diff --git a/src/v2/pdf_resources/page_font.h b/src/v2/pdf_resources/page_font.h
index 06ac6150..e1c4cc63 100644
--- a/src/v2/pdf_resources/page_font.h
+++ b/src/v2/pdf_resources/page_font.h
@@ -103,6 +103,7 @@ namespace pdflib
 
     std::string        encoding_name;
     font_encoding_name encoding;
+    bool               has_explicit_encoding; // true if encoding was found in PDF, false if defaulted
 
     font_subtype_name  subtype;
 
@@ -487,7 +488,14 @@ namespace pdflib
 
         auto& fm = bfonts.get(fontname);
 
-        if(fm.has(c))
+        // If font declares a specific encoding (MacRoman, WinAnsi, etc.) AND it was
+        // explicitly specified in the PDF, use that encoding instead of base font's built-in mapping
+        if(has_explicit_encoding &&
+           (encoding == MACROMAN || encoding == MACEXPERT || encoding == WINANSI || encoding == STANDARD))
+          {
+            return get_character_from_encoding(c);
+          }
+        else if(fm.has(c))
           {
             return fm.to_utf8(c);
           }
@@ -505,14 +513,14 @@ namespace pdflib
 	  {
 	    /*
 	    std::string notdef="GLYPH<"+std::to_string(c)+">";
-	    
+
 	    unknown_numbs[c] += 1;
-	    
+
 	    LOG_S(ERROR) << " Symbol not found in special font: " << c
 			 << "; Encoding: "  << to_string(encoding)
 			 << "; font-name: " << font_name
 			 << " (corresponding font: " << fontname << ")";
-	    
+
 	    return notdef;
 	    */
 
@@ -521,7 +529,7 @@ namespace pdflib
 			   << "; font-name: " << font_name
 			   << " (corresponding font: " << fontname << ")";
 
-	    return get_character_from_encoding(c);	    
+	    return get_character_from_encoding(c);
 	  }
       }
     else
@@ -653,6 +661,7 @@ namespace pdflib
       {
         name = utils::json::get(keys_0, json_font);
         encoding = to_encoding_name(name);
+        has_explicit_encoding = true;
 
         LOG_S(INFO) << "font-encoding [" << name << "]: " << to_string(encoding);
       }
@@ -667,12 +676,13 @@ namespace pdflib
 	    if(cids.has(encoding_name))
 	      {
 		encoding = CMAP_RESOURCES;
+		has_explicit_encoding = true;
 	      }
 	    else if(encoding_name.find("stream") != std::string::npos)
 	      {
 		LOG_S(WARNING) << "font-encoding [" << name << "] contains stream, "
 			       << "falling back to STANDARD encoding";
-		
+
 		/*
 		encoding = to_encoding_name(encoding_name);
 		auto qpdf_obj = qpdf_font.getKey("/Encoding");
@@ -680,12 +690,12 @@ namespace pdflib
 		if(qpdf_obj.isStream())
 		  {
 		    std::vector<qpdf_instruction> stream;
-		    
+
 		    // decode the stream
 		    {
 		      qpdf_stream_decoder decoder(stream);
 		      decoder.decode(qpdf_obj);
-		      
+
 		      decoder.print();
 		    }
 		  }
@@ -695,26 +705,38 @@ namespace pdflib
 		  }
 		*/
 		encoding = STANDARD;
+		has_explicit_encoding = false;
 	      }
 	    else
 	      {
 		encoding = to_encoding_name(encoding_name);
+		has_explicit_encoding = true;
 	      }
 
             LOG_S(INFO) << "font-encoding [" << name << "]: " << to_string(encoding);
           }
+        else if(result.is_object() && result.count("/BaseEncoding") == 1 && result["/BaseEncoding"].is_string())
+          {
+            // Extract /BaseEncoding from encoding dictionary
+            std::string base_enc = result["/BaseEncoding"].get<std::string>();
+            encoding = to_encoding_name(base_enc);
+            has_explicit_encoding = true;
+            LOG_S(INFO) << "font-encoding from object /BaseEncoding [" << base_enc << "]: " << to_string(encoding);
+          }
         else
           {
             LOG_S(WARNING) << "font-encoding [object]: " << result.dump();
             LOG_S(WARNING) << " --> font-encoding falling back to STANDARD";
 
             encoding = STANDARD;
+            has_explicit_encoding = false;
           }
       }
     else
       {
         LOG_S(WARNING) << "font-encoding not defined, falling back to STANDARD";
         encoding = STANDARD;
+        has_explicit_encoding = false;
       }
   }
 
diff --git a/tests/data/cases/cases_11.pdf b/tests/data/cases/cases_11.pdf
new file mode 100644
index 00000000..e0395f36
Binary files /dev/null and b/tests/data/cases/cases_11.pdf differ
diff --git a/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json b/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json
index 37e68c6e..894374f3 100644
--- a/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json
+++ b/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json
@@ -8915,8 +8915,8 @@
         "r_y3": 661.42,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00ba",
-      "orig": "\u00ba",
+      "text": "\u00ce",
+      "orig": "\u00ce",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -41308,8 +41308,8 @@
         "r_y3": 251.389,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a1",
-      "orig": "\u00a1",
+      "text": "\u00b0",
+      "orig": "\u00b0",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -41685,8 +41685,8 @@
         "r_y3": 251.389,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a1",
-      "orig": "\u00a1",
+      "text": "\u00b0",
+      "orig": "\u00b0",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -44034,8 +44034,8 @@
         "r_y3": 103.42,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00b8",
-      "orig": "\u00b8",
+      "text": "\u00c0",
+      "orig": "\u00c0",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -47922,8 +47922,8 @@
         "r_y3": 661.42,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "(l'\u00bale-du-Prince-\u00c9douard,",
-      "orig": "(l'\u00bale-du-Prince-\u00c9douard,",
+      "text": "(l'\u00cele-du-Prince-\u00c9douard,",
+      "orig": "(l'\u00cele-du-Prince-\u00c9douard,",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -52678,8 +52678,8 @@
         "r_y3": 251.389,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "N\u00a1",
-      "orig": "N\u00a1",
+      "text": "N\u00b0",
+      "orig": "N\u00b0",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -52765,8 +52765,8 @@
         "r_y3": 251.389,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "n\u00a1",
-      "orig": "n\u00a1",
+      "text": "n\u00b0",
+      "orig": "n\u00b0",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -53345,8 +53345,8 @@
         "r_y3": 103.42,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00b8",
-      "orig": "\u00b8",
+      "text": "\u00c0",
+      "orig": "\u00c0",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -54246,8 +54246,8 @@
         "r_y3": 661.42,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "(l'\u00bale-du-Prince-\u00c9douard, le Nouveau-Brunswick, la Nouvelle-\u00c9cosse, l'Ontario ou  ",
-      "orig": "(l'\u00bale-du-Prince-\u00c9douard, le Nouveau-Brunswick, la Nouvelle-\u00c9cosse, l'Ontario ou  ",
+      "text": "(l'\u00cele-du-Prince-\u00c9douard, le Nouveau-Brunswick, la Nouvelle-\u00c9cosse, l'Ontario ou  ",
+      "orig": "(l'\u00cele-du-Prince-\u00c9douard, le Nouveau-Brunswick, la Nouvelle-\u00c9cosse, l'Ontario ou  ",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -55029,8 +55029,8 @@
         "r_y3": 251.389,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "N\u00a1 d'unit\u00e9 - n\u00a1 et rue, CP, RR :",
-      "orig": "N\u00a1 d'unit\u00e9 - n\u00a1 et rue, CP, RR :",
+      "text": "N\u00b0 d'unit\u00e9 - n\u00b0 et rue, CP, RR :",
+      "orig": "N\u00b0 d'unit\u00e9 - n\u00b0 et rue, CP, RR :",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -55174,8 +55174,8 @@
         "r_y3": 103.42,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00b8 USAGE INTERNE",
-      "orig": "\u00b8 USAGE INTERNE",
+      "text": "\u00c0 USAGE INTERNE",
+      "orig": "\u00c0 USAGE INTERNE",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
diff --git a/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json.char.txt b/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json.char.txt
index 2c9cc09f..534c8125 100644
--- a/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json.char.txt
+++ b/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json.char.txt
@@ -302,7 +302,7 @@
 (021.00, 652.11) (024.33, 652.11) (024.33, 661.42) (021.00, 661.42)       /TT2 (	<|special_separator|>
 (024.33, 652.11) (026.55, 652.11) (026.55, 661.42) (024.33, 661.42)       /TT2 l	<|special_separator|>
 (026.55, 652.11) (028.46, 652.11) (028.46, 661.42) (026.55, 661.42)       /TT2 '	<|special_separator|>
-(028.46, 652.11) (031.24, 652.11) (031.24, 661.42) (028.46, 661.42)       /TT2 º	<|special_separator|>
+(028.46, 652.11) (031.24, 652.11) (031.24, 661.42) (028.46, 661.42)       /TT2 Î	<|special_separator|>
 (031.24, 652.11) (033.46, 652.11) (033.46, 661.42) (031.24, 661.42)       /TT2 l	<|special_separator|>
 (033.46, 652.11) (039.02, 652.11) (039.02, 661.42) (033.46, 661.42)       /TT2 e	<|special_separator|>
 (039.02, 652.11) (042.35, 652.11) (042.35, 661.42) (039.02, 661.42)       /TT2 -	<|special_separator|>
@@ -1419,7 +1419,7 @@
 (110.80, 264.14) (113.86, 264.14) (113.86, 274.43) (110.80, 274.43)       /TT1 l	<|special_separator|>
 (113.86, 264.14) (119.97, 264.14) (119.97, 274.43) (113.86, 274.43)       /TT1 e	<|special_separator|>
 (035.00, 242.08) (042.22, 242.08) (042.22, 251.39) (035.00, 251.39)       /TT2 N	<|special_separator|>
-(042.22, 242.08) (046.22, 242.08) (046.22, 251.39) (042.22, 251.39)       /TT2 ¡	<|special_separator|>
+(042.22, 242.08) (046.22, 242.08) (046.22, 251.39) (042.22, 251.39)       /TT2 °	<|special_separator|>
 (046.22, 242.08) (049.00, 242.08) (049.00, 251.39) (046.22, 251.39)       /TT2  	<|special_separator|>
 (049.00, 242.08) (054.56, 242.08) (054.56, 251.39) (049.00, 251.39)       /TT2 d	<|special_separator|>
 (054.56, 242.08) (056.47, 242.08) (056.47, 251.39) (054.56, 251.39)       /TT2 '	<|special_separator|>
@@ -1432,7 +1432,7 @@
 (080.93, 242.08) (086.49, 242.08) (086.49, 251.39) (080.93, 251.39)       /TT2 -	<|special_separator|>
 (086.49, 242.08) (089.27, 242.08) (089.27, 251.39) (086.49, 251.39)       /TT2  	<|special_separator|>
 (089.27, 242.08) (094.83, 242.08) (094.83, 251.39) (089.27, 251.39)       /TT2 n	<|special_separator|>
-(094.83, 242.08) (098.83, 242.08) (098.83, 251.39) (094.83, 251.39)       /TT2 ¡	<|special_separator|>
+(094.83, 242.08) (098.83, 242.08) (098.83, 251.39) (094.83, 251.39)       /TT2 °	<|special_separator|>
 (098.83, 242.08) (101.61, 242.08) (101.61, 251.39) (098.83, 251.39)       /TT2  	<|special_separator|>
 (101.61, 242.08) (107.17, 242.08) (107.17, 251.39) (101.61, 251.39)       /TT2 e	<|special_separator|>
 (107.17, 242.08) (109.95, 242.08) (109.95, 251.39) (107.17, 251.39)       /TT2 t	<|special_separator|>
@@ -1513,7 +1513,7 @@
 (052.23, 134.08) (057.23, 134.08) (057.23, 143.39) (052.23, 143.39)       /TT2 s	<|special_separator|>
 (057.23, 134.08) (060.01, 134.08) (060.01, 143.39) (057.23, 143.39)       /TT2  	<|special_separator|>
 (060.01, 134.08) (062.79, 134.08) (062.79, 143.39) (060.01, 143.39)       /TT2 :	<|special_separator|>
-(023.00, 094.07) (030.22, 094.07) (030.22, 103.42) (023.00, 103.42)       /TT1 ¸	<|special_separator|>
+(023.00, 094.07) (030.22, 094.07) (030.22, 103.42) (023.00, 103.42)       /TT1 À	<|special_separator|>
 (030.22, 094.07) (033.00, 094.07) (033.00, 103.42) (030.22, 103.42)       /TT1  	<|special_separator|>
 (033.00, 094.07) (040.22, 094.07) (040.22, 103.42) (033.00, 103.42)       /TT1 U	<|special_separator|>
 (040.22, 094.07) (046.89, 094.07) (046.89, 103.42) (040.22, 103.42)       /TT1 S	<|special_separator|>
diff --git a/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json.line.txt b/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json.line.txt
index d71ce172..4087d238 100644
--- a/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json.line.txt
+++ b/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json.line.txt
@@ -5,7 +5,7 @@
 (502.01, 679.96) (570.21, 679.96) (570.21, 687.41) (502.01, 687.41)       /TT2 N'inscrivez rien ici. 	<|special_separator|>
 (021.00, 674.11) (444.48, 674.11) (444.48, 683.42) (021.00, 683.42)       /TT2 Remplissez ce formulaire pour demander un remboursement si vous avez payé la TVH sur des 	<|special_separator|>
 (021.00, 663.11) (372.26, 663.11) (372.26, 672.42) (021.00, 672.42)       /TT2 produits (les biens meubles corporels) achetés dans une province participante  	<|special_separator|>
-(021.00, 652.11) (384.38, 652.11) (384.38, 661.42) (021.00, 661.42)       /TT2 (l'ºle-du-Prince-Édouard, le Nouveau-Brunswick, la Nouvelle-Écosse, l'Ontario ou  	<|special_separator|>
+(021.00, 652.11) (384.38, 652.11) (384.38, 661.42) (021.00, 661.42)       /TT2 (l'Île-du-Prince-Édouard, le Nouveau-Brunswick, la Nouvelle-Écosse, l'Ontario ou  	<|special_separator|>
 (021.00, 641.11) (427.85, 641.11) (427.85, 650.42) (021.00, 650.42)       /TT2 Terre-Neuve-et-Labrador), et transférés dans une province non participante ou autre région 	<|special_separator|>
 (021.00, 630.11) (414.54, 630.11) (414.54, 639.42) (021.00, 639.42)       /TT2 du Canada ou dans une autre province participante dont le taux de TVH est moins élevé.	<|special_separator|>
 (027.00, 611.57) (078.68, 611.57) (078.68, 620.92) (027.00, 620.92)       /TT1 Remarque 	<|special_separator|>
@@ -32,12 +32,12 @@
 (279.00, 295.08) (317.34, 295.08) (317.34, 304.39) (279.00, 304.39)       /TT2 Français	<|special_separator|>
 (348.00, 295.08) (380.79, 295.08) (380.79, 304.39) (348.00, 304.39)       /TT2 Anglais	<|special_separator|>
 (035.00, 264.14) (119.97, 264.14) (119.97, 274.43) (035.00, 274.43)       /TT1 Adresse postale	<|special_separator|>
-(035.00, 242.08) (172.19, 242.08) (172.19, 251.39) (035.00, 251.39)       /TT2 N¡ d'unité - n¡ et rue, CP, RR :	<|special_separator|>
+(035.00, 242.08) (172.19, 242.08) (172.19, 251.39) (035.00, 251.39)       /TT2 N° d'unité - n° et rue, CP, RR :	<|special_separator|>
 (035.00, 215.08) (059.45, 215.08) (059.45, 224.39) (035.00, 224.39)       /TT2 Ville :	<|special_separator|>
 (035.00, 187.08) (155.05, 187.08) (155.05, 196.39) (035.00, 196.39)       /TT2 Province, territoire ou état :	<|special_separator|>
 (035.00, 161.08) (126.16, 161.08) (126.16, 170.39) (035.00, 170.39)       /TT2 Code postal ou ZIP :	<|special_separator|>
 (035.00, 134.08) (062.79, 134.08) (062.79, 143.39) (035.00, 143.39)       /TT2 Pays :	<|special_separator|>
-(023.00, 094.07) (115.23, 094.07) (115.23, 103.42) (023.00, 103.42)       /TT1 ¸ USAGE INTERNE	<|special_separator|>
+(023.00, 094.07) (115.23, 094.07) (115.23, 103.42) (023.00, 103.42)       /TT1 À USAGE INTERNE	<|special_separator|>
 (023.00, 077.11) (033.00, 077.11) (033.00, 086.42) (023.00, 086.42)       /TT2 IC	<|special_separator|>
 (199.78, 077.11) (214.22, 077.11) (214.22, 086.42) (199.78, 086.42)       /TT2 NC	<|special_separator|>
 (021.00, 019.09) (074.35, 019.09) (074.35, 026.54) (021.00, 026.54)       /TT2 GST495 F (24)	<|special_separator|>
diff --git a/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json.word.txt b/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json.word.txt
index 8b242483..c2c19081 100644
--- a/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json.word.txt
+++ b/tests/data/groundtruth/form_fields.pdf.page_no_1.py.json.word.txt
@@ -45,7 +45,7 @@
 (254.98, 663.11) (271.66, 663.11) (271.66, 672.42) (254.98, 672.42)       /TT2 une	<|special_separator|>
 (274.44, 663.11) (312.23, 663.11) (312.23, 672.42) (274.44, 672.42)       /TT2 province	<|special_separator|>
 (315.01, 663.11) (366.70, 663.11) (366.70, 672.42) (315.01, 672.42)       /TT2 participante	<|special_separator|>
-(021.00, 652.11) (129.05, 652.11) (129.05, 661.42) (021.00, 661.42)       /TT2 (l'ºle-du-Prince-Édouard,	<|special_separator|>
+(021.00, 652.11) (129.05, 652.11) (129.05, 661.42) (021.00, 661.42)       /TT2 (l'Île-du-Prince-Édouard,	<|special_separator|>
 (131.83, 652.11) (139.61, 652.11) (139.61, 661.42) (131.83, 661.42)       /TT2 le	<|special_separator|>
 (142.39, 652.11) (234.08, 652.11) (234.08, 661.42) (142.39, 661.42)       /TT2 Nouveau-Brunswick,	<|special_separator|>
 (236.86, 652.11) (244.64, 652.11) (244.64, 661.42) (236.86, 661.42)       /TT2 la	<|special_separator|>
@@ -209,10 +209,10 @@
 (348.00, 295.08) (380.79, 295.08) (380.79, 304.39) (348.00, 304.39)       /TT2 Anglais	<|special_separator|>
 (035.00, 264.14) (078.40, 264.14) (078.40, 274.43) (035.00, 274.43)       /TT1 Adresse	<|special_separator|>
 (081.46, 264.14) (119.97, 264.14) (119.97, 274.43) (081.46, 274.43)       /TT1 postale	<|special_separator|>
-(035.00, 242.08) (046.22, 242.08) (046.22, 251.39) (035.00, 251.39)       /TT2 N¡	<|special_separator|>
+(035.00, 242.08) (046.22, 242.08) (046.22, 251.39) (035.00, 251.39)       /TT2 N°	<|special_separator|>
 (049.00, 242.08) (078.15, 242.08) (078.15, 251.39) (049.00, 251.39)       /TT2 d'unité	<|special_separator|>
 (080.93, 242.08) (086.49, 242.08) (086.49, 251.39) (080.93, 251.39)       /TT2 -	<|special_separator|>
-(089.27, 242.08) (098.83, 242.08) (098.83, 251.39) (089.27, 251.39)       /TT2 n¡	<|special_separator|>
+(089.27, 242.08) (098.83, 242.08) (098.83, 251.39) (089.27, 251.39)       /TT2 n°	<|special_separator|>
 (101.61, 242.08) (109.95, 242.08) (109.95, 251.39) (101.61, 251.39)       /TT2 et	<|special_separator|>
 (112.73, 242.08) (129.96, 242.08) (129.96, 251.39) (112.73, 251.39)       /TT2 rue,	<|special_separator|>
 (132.74, 242.08) (149.41, 242.08) (149.41, 251.39) (132.74, 251.39)       /TT2 CP,	<|special_separator|>
@@ -232,7 +232,7 @@
 (123.38, 161.08) (126.16, 161.08) (126.16, 170.39) (123.38, 170.39)       /TT2 :	<|special_separator|>
 (035.00, 134.08) (057.23, 134.08) (057.23, 143.39) (035.00, 143.39)       /TT2 Pays	<|special_separator|>
 (060.01, 134.08) (062.79, 134.08) (062.79, 143.39) (060.01, 143.39)       /TT2 :	<|special_separator|>
-(023.00, 094.07) (030.22, 094.07) (030.22, 103.42) (023.00, 103.42)       /TT1 ¸	<|special_separator|>
+(023.00, 094.07) (030.22, 094.07) (030.22, 103.42) (023.00, 103.42)       /TT1 À	<|special_separator|>
 (033.00, 094.07) (068.56, 094.07) (068.56, 103.42) (033.00, 103.42)       /TT1 USAGE	<|special_separator|>
 (071.34, 094.07) (115.23, 094.07) (115.23, 103.42) (071.34, 103.42)       /TT1 INTERNE	<|special_separator|>
 (023.00, 077.11) (033.00, 077.11) (033.00, 086.42) (023.00, 086.42)       /TT2 IC	<|special_separator|>
diff --git a/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json b/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json
index bc1ce0b4..495b829c 100644
--- a/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json
+++ b/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json
@@ -3666,8 +3666,8 @@
         "r_y3": 698.39,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a1",
-      "orig": "\u00a1",
+      "text": "\u00b0",
+      "orig": "\u00b0",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -4043,8 +4043,8 @@
         "r_y3": 698.39,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a1",
-      "orig": "\u00a1",
+      "text": "\u00b0",
+      "orig": "\u00b0",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -31276,8 +31276,8 @@
         "r_y3": 698.39,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "N\u00a1",
-      "orig": "N\u00a1",
+      "text": "N\u00b0",
+      "orig": "N\u00b0",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -31363,8 +31363,8 @@
         "r_y3": 698.39,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "n\u00a1",
-      "orig": "n\u00a1",
+      "text": "n\u00b0",
+      "orig": "n\u00b0",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -35889,8 +35889,8 @@
         "r_y3": 698.39,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "N\u00a1 d'unit\u00e9 - n\u00a1 et rue, RR :",
-      "orig": "N\u00a1 d'unit\u00e9 - n\u00a1 et rue, RR :",
+      "text": "N\u00b0 d'unit\u00e9 - n\u00b0 et rue, RR :",
+      "orig": "N\u00b0 d'unit\u00e9 - n\u00b0 et rue, RR :",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
diff --git a/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json.char.txt b/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json.char.txt
index ed51d37e..582c5670 100644
--- a/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json.char.txt
+++ b/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json.char.txt
@@ -122,7 +122,7 @@
 (287.76, 711.64) (293.87, 711.64) (293.87, 721.88) (287.76, 721.88)       /TT2 e	<|special_separator|>
 (293.87, 711.64) (297.54, 711.64) (297.54, 721.88) (293.87, 721.88)       /TT2 )	<|special_separator|>
 (035.00, 689.08) (042.22, 689.08) (042.22, 698.39) (035.00, 698.39)       /TT2 N	<|special_separator|>
-(042.22, 689.08) (046.22, 689.08) (046.22, 698.39) (042.22, 698.39)       /TT2 ¡	<|special_separator|>
+(042.22, 689.08) (046.22, 689.08) (046.22, 698.39) (042.22, 698.39)       /TT2 °	<|special_separator|>
 (046.22, 689.08) (049.00, 689.08) (049.00, 698.39) (046.22, 698.39)       /TT2  	<|special_separator|>
 (049.00, 689.08) (054.56, 689.08) (054.56, 698.39) (049.00, 698.39)       /TT2 d	<|special_separator|>
 (054.56, 689.08) (056.47, 689.08) (056.47, 698.39) (054.56, 698.39)       /TT2 '	<|special_separator|>
@@ -135,7 +135,7 @@
 (080.93, 689.08) (086.49, 689.08) (086.49, 698.39) (080.93, 698.39)       /TT2 -	<|special_separator|>
 (086.49, 689.08) (089.27, 689.08) (089.27, 698.39) (086.49, 698.39)       /TT2  	<|special_separator|>
 (089.27, 689.08) (094.83, 689.08) (094.83, 698.39) (089.27, 698.39)       /TT2 n	<|special_separator|>
-(094.83, 689.08) (098.83, 689.08) (098.83, 698.39) (094.83, 698.39)       /TT2 ¡	<|special_separator|>
+(094.83, 689.08) (098.83, 689.08) (098.83, 698.39) (094.83, 698.39)       /TT2 °	<|special_separator|>
 (098.83, 689.08) (101.61, 689.08) (101.61, 698.39) (098.83, 698.39)       /TT2  	<|special_separator|>
 (101.61, 689.08) (107.17, 689.08) (107.17, 698.39) (101.61, 698.39)       /TT2 e	<|special_separator|>
 (107.17, 689.08) (109.95, 689.08) (109.95, 698.39) (107.17, 698.39)       /TT2 t	<|special_separator|>
diff --git a/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json.line.txt b/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json.line.txt
index a73c6cb0..7ce9a6d8 100644
--- a/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json.line.txt
+++ b/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json.line.txt
@@ -4,7 +4,7 @@
 (246.50, 737.11) (274.28, 737.11) (274.28, 746.42) (246.50, 746.42)       /TT2 (suite)	<|special_separator|>
 (035.00, 711.63) (132.81, 711.63) (132.81, 721.91) (035.00, 721.91)       /TT1 Adresse physique 	<|special_separator|>
 (132.81, 711.64) (297.54, 711.64) (297.54, 721.88) (132.81, 721.88)       /TT2 (si différente de l'adresse postale)	<|special_separator|>
-(035.00, 689.08) (152.74, 689.08) (152.74, 698.39) (035.00, 698.39)       /TT2 N¡ d'unité - n¡ et rue, RR :	<|special_separator|>
+(035.00, 689.08) (152.74, 689.08) (152.74, 698.39) (035.00, 698.39)       /TT2 N° d'unité - n° et rue, RR :	<|special_separator|>
 (035.00, 662.08) (059.45, 662.08) (059.45, 671.39) (035.00, 671.39)       /TT2 Ville :	<|special_separator|>
 (035.00, 634.08) (155.05, 634.08) (155.05, 643.39) (035.00, 643.39)       /TT2 Province, territoire ou état :	<|special_separator|>
 (035.00, 608.08) (126.16, 608.08) (126.16, 617.39) (035.00, 617.39)       /TT2 Code postal ou ZIP :	<|special_separator|>
diff --git a/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json.word.txt b/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json.word.txt
index 6601c496..6e0ea2bb 100644
--- a/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json.word.txt
+++ b/tests/data/groundtruth/form_fields.pdf.page_no_2.py.json.word.txt
@@ -17,10 +17,10 @@
 (196.39, 711.64) (208.62, 711.64) (208.62, 721.88) (196.39, 721.88)       /TT2 de	<|special_separator|>
 (211.68, 711.64) (255.35, 711.64) (255.35, 721.88) (211.68, 721.88)       /TT2 l'adresse	<|special_separator|>
 (258.41, 711.64) (297.54, 711.64) (297.54, 721.88) (258.41, 721.88)       /TT2 postale)	<|special_separator|>
-(035.00, 689.08) (046.22, 689.08) (046.22, 698.39) (035.00, 698.39)       /TT2 N¡	<|special_separator|>
+(035.00, 689.08) (046.22, 689.08) (046.22, 698.39) (035.00, 698.39)       /TT2 N°	<|special_separator|>
 (049.00, 689.08) (078.15, 689.08) (078.15, 698.39) (049.00, 698.39)       /TT2 d'unité	<|special_separator|>
 (080.93, 689.08) (086.49, 689.08) (086.49, 698.39) (080.93, 698.39)       /TT2 -	<|special_separator|>
-(089.27, 689.08) (098.83, 689.08) (098.83, 698.39) (089.27, 698.39)       /TT2 n¡	<|special_separator|>
+(089.27, 689.08) (098.83, 689.08) (098.83, 698.39) (089.27, 698.39)       /TT2 n°	<|special_separator|>
 (101.61, 689.08) (109.95, 689.08) (109.95, 698.39) (101.61, 698.39)       /TT2 et	<|special_separator|>
 (112.73, 689.08) (129.96, 689.08) (129.96, 698.39) (112.73, 698.39)       /TT2 rue,	<|special_separator|>
 (132.74, 689.08) (147.18, 689.08) (147.18, 698.39) (132.74, 698.39)       /TT2 RR	<|special_separator|>
diff --git a/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json b/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json
index c4150feb..79fd6712 100644
--- a/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json
+++ b/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json
@@ -6624,8 +6624,8 @@
         "r_y3": 685.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -7581,8 +7581,8 @@
         "r_y3": 670.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -10597,8 +10597,8 @@
         "r_y3": 643.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -15382,8 +15382,8 @@
         "r_y3": 607.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -25271,8 +25271,8 @@
         "r_y3": 538.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -29592,8 +29592,8 @@
         "r_y3": 502.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -34435,8 +34435,8 @@
         "r_y3": 466.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -36436,8 +36436,8 @@
         "r_y3": 439.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -59868,8 +59868,8 @@
         "r_y3": 226.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -61028,8 +61028,8 @@
         "r_y3": 211.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -62710,8 +62710,8 @@
         "r_y3": 196.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -65813,8 +65813,8 @@
         "r_y3": 169.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -103310,8 +103310,8 @@
         "r_y3": 505.888,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u02d9",
-      "orig": "\u02d9",
+      "text": "\u00ab",
+      "orig": "\u00ab",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -104122,8 +104122,8 @@
         "r_y3": 505.888,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a8",
-      "orig": "\u00a8",
+      "text": "\u00bb",
+      "orig": "\u00bb",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -137387,8 +137387,8 @@
         "r_y3": 685.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -137590,8 +137590,8 @@
         "r_y3": 670.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -138141,8 +138141,8 @@
         "r_y3": 643.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -138895,8 +138895,8 @@
         "r_y3": 607.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -140577,8 +140577,8 @@
         "r_y3": 538.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -141302,8 +141302,8 @@
         "r_y3": 502.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -142201,8 +142201,8 @@
         "r_y3": 466.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -142607,8 +142607,8 @@
         "r_y3": 439.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -146377,8 +146377,8 @@
         "r_y3": 226.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -146609,8 +146609,8 @@
         "r_y3": 211.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -146870,8 +146870,8 @@
         "r_y3": 196.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -147392,8 +147392,8 @@
         "r_y3": 169.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -153337,8 +153337,8 @@
         "r_y3": 505.888,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u02d9",
-      "orig": "\u02d9",
+      "text": "\u00ab",
+      "orig": "\u00ab",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -153453,8 +153453,8 @@
         "r_y3": 505.888,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a8",
-      "orig": "\u00a8",
+      "text": "\u00bb",
+      "orig": "\u00bb",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -158675,8 +158675,8 @@
         "r_y3": 685.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5 Vous \u00eates un r\u00e9sident du Canada.",
-      "orig": "\u00a5 Vous \u00eates un r\u00e9sident du Canada.",
+      "text": "\u2022 Vous \u00eates un r\u00e9sident du Canada.",
+      "orig": "\u2022 Vous \u00eates un r\u00e9sident du Canada.",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -158704,8 +158704,8 @@
         "r_y3": 670.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5 Vous avez achet\u00e9 les produits dans une province ",
-      "orig": "\u00a5 Vous avez achet\u00e9 les produits dans une province ",
+      "text": "\u2022 Vous avez achet\u00e9 les produits dans une province ",
+      "orig": "\u2022 Vous avez achet\u00e9 les produits dans une province ",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -158762,8 +158762,8 @@
         "r_y3": 643.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5 Vous avez achet\u00e9 les produits pour les consommer, les ",
-      "orig": "\u00a5 Vous avez achet\u00e9 les produits pour les consommer, les ",
+      "text": "\u2022 Vous avez achet\u00e9 les produits pour les consommer, les ",
+      "orig": "\u2022 Vous avez achet\u00e9 les produits pour les consommer, les ",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -158849,8 +158849,8 @@
         "r_y3": 607.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5 Vous avez transf\u00e9r\u00e9 les produits d'une province ",
-      "orig": "\u00a5 Vous avez transf\u00e9r\u00e9 les produits d'une province ",
+      "text": "\u2022 Vous avez transf\u00e9r\u00e9 les produits d'une province ",
+      "orig": "\u2022 Vous avez transf\u00e9r\u00e9 les produits d'une province ",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -159023,8 +159023,8 @@
         "r_y3": 538.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5 Vous avez pay\u00e9 les taxes provinciales applicables de la ",
-      "orig": "\u00a5 Vous avez pay\u00e9 les taxes provinciales applicables de la ",
+      "text": "\u2022 Vous avez pay\u00e9 les taxes provinciales applicables de la ",
+      "orig": "\u2022 Vous avez pay\u00e9 les taxes provinciales applicables de la ",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -159110,8 +159110,8 @@
         "r_y3": 502.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5 Si vous \u00eates un consommateur du bien (sauf les ",
-      "orig": "\u00a5 Si vous \u00eates un consommateur du bien (sauf les ",
+      "text": "\u2022 Si vous \u00eates un consommateur du bien (sauf les ",
+      "orig": "\u2022 Si vous \u00eates un consommateur du bien (sauf les ",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -159255,8 +159255,8 @@
         "r_y3": 466.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -159371,8 +159371,8 @@
         "r_y3": 439.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5",
-      "orig": "\u00a5",
+      "text": "\u2022",
+      "orig": "\u2022",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -160183,8 +160183,8 @@
         "r_y3": 226.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5 les copies des re\u00e7us pour chaque achat;",
-      "orig": "\u00a5 les copies des re\u00e7us pour chaque achat;",
+      "text": "\u2022 les copies des re\u00e7us pour chaque achat;",
+      "orig": "\u2022 les copies des re\u00e7us pour chaque achat;",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -160212,8 +160212,8 @@
         "r_y3": 211.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5 la preuve de paiement des taxes provinciales applicables;",
-      "orig": "\u00a5 la preuve de paiement des taxes provinciales applicables;",
+      "text": "\u2022 la preuve de paiement des taxes provinciales applicables;",
+      "orig": "\u2022 la preuve de paiement des taxes provinciales applicables;",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -160241,8 +160241,8 @@
         "r_y3": 196.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5 si le produit admissible \u00e9tait entrepos\u00e9, les copies des ",
-      "orig": "\u00a5 si le produit admissible \u00e9tait entrepos\u00e9, les copies des ",
+      "text": "\u2022 si le produit admissible \u00e9tait entrepos\u00e9, les copies des ",
+      "orig": "\u2022 si le produit admissible \u00e9tait entrepos\u00e9, les copies des ",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -160299,8 +160299,8 @@
         "r_y3": 169.918,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "\u00a5 dans le cas d'un v\u00e9hicule \u00e0 moteur d\u00e9termin\u00e9 qui est ",
-      "orig": "\u00a5 dans le cas d'un v\u00e9hicule \u00e0 moteur d\u00e9termin\u00e9 qui est ",
+      "text": "\u2022 dans le cas d'un v\u00e9hicule \u00e0 moteur d\u00e9termin\u00e9 qui est ",
+      "orig": "\u2022 dans le cas d'un v\u00e9hicule \u00e0 moteur d\u00e9termin\u00e9 qui est ",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
@@ -161285,8 +161285,8 @@
         "r_y3": 505.888,
         "coord_origin": "BOTTOMLEFT"
       },
-      "text": "service \u02d9 Produire un remboursement \u00a8 dans Mon dossier ",
-      "orig": "service \u02d9 Produire un remboursement \u00a8 dans Mon dossier ",
+      "text": "service \u00ab Produire un remboursement \u00bb dans Mon dossier ",
+      "orig": "service \u00ab Produire un remboursement \u00bb dans Mon dossier ",
       "text_direction": "left_to_right",
       "confidence": 1.0,
       "from_ocr": false,
diff --git a/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json.char.txt b/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json.char.txt
index 9a118d27..2c371d29 100644
--- a/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json.char.txt
+++ b/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json.char.txt
@@ -224,7 +224,7 @@
 (286.65, 694.58) (291.65, 694.58) (291.65, 703.89) (286.65, 703.89)       /TT2 s	<|special_separator|>
 (291.65, 694.58) (294.43, 694.58) (294.43, 703.89) (291.65, 703.89)       /TT2  	<|special_separator|>
 (294.43, 694.58) (297.21, 694.58) (297.21, 703.89) (294.43, 703.89)       /TT2 :	<|special_separator|>
-(027.00, 676.61) (030.50, 676.61) (030.50, 685.92) (027.00, 685.92)       /TT2 ¥	<|special_separator|>
+(027.00, 676.61) (030.50, 676.61) (030.50, 685.92) (027.00, 685.92)       /TT2 •	<|special_separator|>
 (033.00, 677.11) (039.67, 677.11) (039.67, 686.42) (033.00, 686.42)       /TT2 V	<|special_separator|>
 (039.67, 677.11) (045.23, 677.11) (045.23, 686.42) (039.67, 686.42)       /TT2 o	<|special_separator|>
 (045.23, 677.11) (050.79, 677.11) (050.79, 686.42) (045.23, 686.42)       /TT2 u	<|special_separator|>
@@ -257,7 +257,7 @@
 (170.30, 677.11) (175.86, 677.11) (175.86, 686.42) (170.30, 686.42)       /TT2 d	<|special_separator|>
 (175.86, 677.11) (181.42, 677.11) (181.42, 686.42) (175.86, 686.42)       /TT2 a	<|special_separator|>
 (181.42, 677.11) (184.20, 677.11) (184.20, 686.42) (181.42, 686.42)       /TT2 .	<|special_separator|>
-(027.00, 661.61) (030.50, 661.61) (030.50, 670.92) (027.00, 670.92)       /TT2 ¥	<|special_separator|>
+(027.00, 661.61) (030.50, 661.61) (030.50, 670.92) (027.00, 670.92)       /TT2 •	<|special_separator|>
 (033.00, 662.11) (039.67, 662.11) (039.67, 671.42) (033.00, 671.42)       /TT2 V	<|special_separator|>
 (039.67, 662.11) (045.23, 662.11) (045.23, 671.42) (039.67, 671.42)       /TT2 o	<|special_separator|>
 (045.23, 662.11) (050.79, 662.11) (050.79, 671.42) (045.23, 671.42)       /TT2 u	<|special_separator|>
@@ -361,7 +361,7 @@
 (266.99, 651.11) (269.77, 651.11) (269.77, 660.42) (266.99, 660.42)       /TT2 t	<|special_separator|>
 (269.77, 651.11) (274.77, 651.11) (274.77, 660.42) (269.77, 660.42)       /TT2 s	<|special_separator|>
 (274.77, 651.11) (277.55, 651.11) (277.55, 660.42) (274.77, 660.42)       /TT2 .	<|special_separator|>
-(027.00, 634.61) (030.50, 634.61) (030.50, 643.92) (027.00, 643.92)       /TT2 ¥	<|special_separator|>
+(027.00, 634.61) (030.50, 634.61) (030.50, 643.92) (027.00, 643.92)       /TT2 •	<|special_separator|>
 (033.00, 635.11) (039.67, 635.11) (039.67, 644.42) (033.00, 644.42)       /TT2 V	<|special_separator|>
 (039.67, 635.11) (045.23, 635.11) (045.23, 644.42) (039.67, 644.42)       /TT2 o	<|special_separator|>
 (045.23, 635.11) (050.79, 635.11) (050.79, 644.42) (045.23, 644.42)       /TT2 u	<|special_separator|>
@@ -526,7 +526,7 @@
 (233.88, 613.11) (236.66, 613.11) (236.66, 622.42) (233.88, 622.42)       /TT2 t	<|special_separator|>
 (236.66, 613.11) (242.22, 613.11) (242.22, 622.42) (236.66, 622.42)       /TT2 e	<|special_separator|>
 (242.22, 613.11) (245.00, 613.11) (245.00, 622.42) (242.22, 622.42)       /TT2 .	<|special_separator|>
-(027.00, 598.61) (030.50, 598.61) (030.50, 607.92) (027.00, 607.92)       /TT2 ¥	<|special_separator|>
+(027.00, 598.61) (030.50, 598.61) (030.50, 607.92) (027.00, 607.92)       /TT2 •	<|special_separator|>
 (033.00, 599.11) (039.67, 599.11) (039.67, 608.42) (033.00, 608.42)       /TT2 V	<|special_separator|>
 (039.67, 599.11) (045.23, 599.11) (045.23, 608.42) (039.67, 608.42)       /TT2 o	<|special_separator|>
 (045.23, 599.11) (050.79, 599.11) (050.79, 608.42) (045.23, 608.42)       /TT2 u	<|special_separator|>
@@ -867,7 +867,7 @@
 (273.35, 544.11) (278.35, 544.11) (278.35, 553.42) (273.35, 553.42)       /TT2 s	<|special_separator|>
 (278.35, 544.11) (281.68, 544.11) (281.68, 553.42) (278.35, 553.42)       /TT2 )	<|special_separator|>
 (281.68, 544.11) (284.46, 544.11) (284.46, 553.42) (281.68, 553.42)       /TT2 .	<|special_separator|>
-(027.00, 529.61) (030.50, 529.61) (030.50, 538.92) (027.00, 538.92)       /TT2 ¥	<|special_separator|>
+(027.00, 529.61) (030.50, 529.61) (030.50, 538.92) (027.00, 538.92)       /TT2 •	<|special_separator|>
 (033.00, 530.11) (039.67, 530.11) (039.67, 539.42) (033.00, 539.42)       /TT2 V	<|special_separator|>
 (039.67, 530.11) (045.23, 530.11) (045.23, 539.42) (039.67, 539.42)       /TT2 o	<|special_separator|>
 (045.23, 530.11) (050.79, 530.11) (050.79, 539.42) (045.23, 539.42)       /TT2 u	<|special_separator|>
@@ -1016,7 +1016,7 @@
 (168.07, 508.11) (173.63, 508.11) (173.63, 517.42) (168.07, 517.42)       /TT2 é	<|special_separator|>
 (173.63, 508.11) (178.63, 508.11) (178.63, 517.42) (173.63, 517.42)       /TT2 s	<|special_separator|>
 (178.63, 508.11) (181.41, 508.11) (181.41, 517.42) (178.63, 517.42)       /TT2 .	<|special_separator|>
-(027.00, 493.61) (030.50, 493.61) (030.50, 502.92) (027.00, 502.92)       /TT2 ¥	<|special_separator|>
+(027.00, 493.61) (030.50, 493.61) (030.50, 502.92) (027.00, 502.92)       /TT2 •	<|special_separator|>
 (033.00, 494.58) (039.67, 494.58) (039.67, 503.89) (033.00, 503.89)       /TT2 S	<|special_separator|>
 (039.67, 494.58) (041.89, 494.58) (041.89, 503.89) (039.67, 503.89)       /TT2 i	<|special_separator|>
 (041.89, 494.58) (044.67, 494.58) (044.67, 503.89) (041.89, 503.89)       /TT2  	<|special_separator|>
@@ -1183,7 +1183,7 @@
 (268.13, 472.58) (273.69, 472.58) (273.69, 481.89) (268.13, 481.89)       /TT2 n	<|special_separator|>
 (273.69, 472.58) (278.69, 472.58) (278.69, 481.89) (273.69, 481.89)       /TT2 s	<|special_separator|>
 (278.69, 472.58) (281.47, 472.58) (281.47, 481.89) (278.69, 481.89)       /TT2 .	<|special_separator|>
-(027.00, 457.61) (030.50, 457.61) (030.50, 466.92) (027.00, 466.92)       /TT2 ¥	<|special_separator|>
+(027.00, 457.61) (030.50, 457.61) (030.50, 466.92) (027.00, 466.92)       /TT2 •	<|special_separator|>
 (033.00, 458.57) (040.22, 458.57) (040.22, 467.92) (033.00, 467.92)       /TT1 C	<|special_separator|>
 (040.22, 458.57) (046.33, 458.57) (046.33, 467.92) (040.22, 467.92)       /TT1 h	<|special_separator|>
 (046.33, 458.57) (051.89, 458.57) (051.89, 467.92) (046.33, 467.92)       /TT1 a	<|special_separator|>
@@ -1252,7 +1252,7 @@
 (102.47, 447.58) (105.25, 447.58) (105.25, 456.89) (102.47, 456.89)       /TT2  	<|special_separator|>
 (105.25, 447.58) (110.81, 447.58) (110.81, 456.89) (105.25, 456.89)       /TT2 $	<|special_separator|>
 (110.81, 447.58) (113.59, 447.58) (113.59, 456.89) (110.81, 456.89)       /TT2 .	<|special_separator|>
-(027.00, 430.61) (030.50, 430.61) (030.50, 439.92) (027.00, 439.92)       /TT2 ¥	<|special_separator|>
+(027.00, 430.61) (030.50, 430.61) (030.50, 439.92) (027.00, 439.92)       /TT2 •	<|special_separator|>
 (033.00, 431.57) (039.11, 431.57) (039.11, 440.92) (033.00, 440.92)       /TT1 L	<|special_separator|>
 (039.11, 431.57) (044.67, 431.57) (044.67, 440.92) (039.11, 440.92)       /TT1 e	<|special_separator|>
 (044.67, 431.57) (047.45, 431.57) (047.45, 440.92) (044.67, 440.92)       /TT1  	<|special_separator|>
@@ -2060,7 +2060,7 @@
 (057.13, 237.11) (062.69, 237.11) (062.69, 246.42) (057.13, 246.42)       /TT2 e	<|special_separator|>
 (062.69, 237.11) (065.47, 237.11) (065.47, 246.42) (062.69, 246.42)       /TT2  	<|special_separator|>
 (065.47, 237.11) (068.25, 237.11) (068.25, 246.42) (065.47, 246.42)       /TT2 :	<|special_separator|>
-(027.00, 217.61) (030.50, 217.61) (030.50, 226.92) (027.00, 226.92)       /TT2 ¥	<|special_separator|>
+(027.00, 217.61) (030.50, 217.61) (030.50, 226.92) (027.00, 226.92)       /TT2 •	<|special_separator|>
 (033.00, 218.11) (035.22, 218.11) (035.22, 227.42) (033.00, 227.42)       /TT2 l	<|special_separator|>
 (035.22, 218.11) (040.78, 218.11) (040.78, 227.42) (035.22, 227.42)       /TT2 e	<|special_separator|>
 (040.78, 218.11) (045.78, 218.11) (045.78, 227.42) (040.78, 227.42)       /TT2 s	<|special_separator|>
@@ -2100,7 +2100,7 @@
 (200.86, 218.11) (206.42, 218.11) (206.42, 227.42) (200.86, 227.42)       /TT2 a	<|special_separator|>
 (206.42, 218.11) (209.20, 218.11) (209.20, 227.42) (206.42, 227.42)       /TT2 t	<|special_separator|>
 (209.20, 218.11) (211.98, 218.11) (211.98, 227.42) (209.20, 227.42)       /TT2 ;	<|special_separator|>
-(027.00, 202.61) (030.50, 202.61) (030.50, 211.92) (027.00, 211.92)       /TT2 ¥	<|special_separator|>
+(027.00, 202.61) (030.50, 202.61) (030.50, 211.92) (027.00, 211.92)       /TT2 •	<|special_separator|>
 (033.00, 203.11) (035.22, 203.11) (035.22, 212.42) (033.00, 212.42)       /TT2 l	<|special_separator|>
 (035.22, 203.11) (040.78, 203.11) (040.78, 212.42) (035.22, 212.42)       /TT2 a	<|special_separator|>
 (040.78, 203.11) (043.56, 203.11) (043.56, 212.42) (040.78, 212.42)       /TT2  	<|special_separator|>
@@ -2158,7 +2158,7 @@
 (275.33, 203.11) (280.89, 203.11) (280.89, 212.42) (275.33, 212.42)       /TT2 e	<|special_separator|>
 (280.89, 203.11) (285.89, 203.11) (285.89, 212.42) (280.89, 212.42)       /TT2 s	<|special_separator|>
 (285.89, 203.11) (288.67, 203.11) (288.67, 212.42) (285.89, 212.42)       /TT2 ;	<|special_separator|>
-(027.00, 187.61) (030.50, 187.61) (030.50, 196.92) (027.00, 196.92)       /TT2 ¥	<|special_separator|>
+(027.00, 187.61) (030.50, 187.61) (030.50, 196.92) (027.00, 196.92)       /TT2 •	<|special_separator|>
 (033.00, 188.11) (038.00, 188.11) (038.00, 197.42) (033.00, 197.42)       /TT2 s	<|special_separator|>
 (038.00, 188.11) (040.22, 188.11) (040.22, 197.42) (038.00, 197.42)       /TT2 i	<|special_separator|>
 (040.22, 188.11) (043.00, 188.11) (043.00, 197.42) (040.22, 197.42)       /TT2  	<|special_separator|>
@@ -2265,7 +2265,7 @@
 (222.78, 177.11) (228.34, 177.11) (228.34, 186.42) (222.78, 186.42)       /TT2 g	<|special_separator|>
 (228.34, 177.11) (233.90, 177.11) (233.90, 186.42) (228.34, 186.42)       /TT2 e	<|special_separator|>
 (233.90, 177.11) (236.68, 177.11) (236.68, 186.42) (233.90, 186.42)       /TT2 .	<|special_separator|>
-(027.00, 160.61) (030.50, 160.61) (030.50, 169.92) (027.00, 169.92)       /TT2 ¥	<|special_separator|>
+(027.00, 160.61) (030.50, 160.61) (030.50, 169.92) (027.00, 169.92)       /TT2 •	<|special_separator|>
 (033.00, 161.11) (038.56, 161.11) (038.56, 170.42) (033.00, 170.42)       /TT2 d	<|special_separator|>
 (038.56, 161.11) (044.12, 161.11) (044.12, 170.42) (038.56, 170.42)       /TT2 a	<|special_separator|>
 (044.12, 161.11) (049.68, 161.11) (049.68, 170.42) (044.12, 170.42)       /TT2 n	<|special_separator|>
@@ -3558,7 +3558,7 @@
 (336.11, 496.58) (341.11, 496.58) (341.11, 505.89) (336.11, 505.89)       /TT2 c	<|special_separator|>
 (341.11, 496.58) (346.67, 496.58) (346.67, 505.89) (341.11, 505.89)       /TT2 e	<|special_separator|>
 (346.67, 496.58) (349.45, 496.58) (349.45, 505.89) (346.67, 505.89)       /TT2  	<|special_separator|>
-(349.45, 496.58) (355.01, 496.58) (355.01, 505.89) (349.45, 505.89)       /TT2 ˙	<|special_separator|>
+(349.45, 496.58) (355.01, 496.58) (355.01, 505.89) (349.45, 505.89)       /TT2 «	<|special_separator|>
 (355.01, 496.58) (357.79, 496.58) (357.79, 505.89) (355.01, 505.89)       /TT2  	<|special_separator|>
 (357.79, 496.58) (364.46, 496.58) (364.46, 505.89) (357.79, 505.89)       /TT2 P	<|special_separator|>
 (364.46, 496.58) (367.79, 496.58) (367.79, 505.89) (364.46, 505.89)       /TT2 r	<|special_separator|>
@@ -3586,7 +3586,7 @@
 (473.94, 496.58) (479.50, 496.58) (479.50, 505.89) (473.94, 505.89)       /TT2 n	<|special_separator|>
 (479.50, 496.58) (482.28, 496.58) (482.28, 505.89) (479.50, 505.89)       /TT2 t	<|special_separator|>
 (482.28, 496.58) (485.06, 496.58) (485.06, 505.89) (482.28, 505.89)       /TT2  	<|special_separator|>
-(485.06, 496.58) (490.62, 496.58) (490.62, 505.89) (485.06, 505.89)       /TT2 ¨	<|special_separator|>
+(485.06, 496.58) (490.62, 496.58) (490.62, 505.89) (485.06, 505.89)       /TT2 »	<|special_separator|>
 (490.62, 496.58) (493.40, 496.58) (493.40, 505.89) (490.62, 505.89)       /TT2  	<|special_separator|>
 (493.40, 496.58) (498.96, 496.58) (498.96, 505.89) (493.40, 505.89)       /TT2 d	<|special_separator|>
 (498.96, 496.58) (504.52, 496.58) (504.52, 505.89) (498.96, 505.89)       /TT2 a	<|special_separator|>
diff --git a/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json.line.txt b/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json.line.txt
index f6dc2bc6..c39d798e 100644
--- a/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json.line.txt
+++ b/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json.line.txt
@@ -7,31 +7,31 @@
 (078.25, 694.58) (091.03, 694.58) (091.03, 703.89) (078.25, 703.89)       /TT2  si 	<|special_separator|>
 (091.03, 694.57) (121.03, 694.57) (121.03, 703.92) (091.03, 703.92)       /TT1 toutes	<|special_separator|>
 (121.03, 694.58) (297.21, 694.58) (297.21, 703.89) (121.03, 703.89)       /TT2  les conditions suivantes sont remplies :	<|special_separator|>
-(027.00, 676.61) (184.20, 677.11) (184.20, 686.42) (027.00, 685.92)       /TT2 ¥ Vous êtes un résident du Canada.	<|special_separator|>
-(027.00, 661.61) (253.67, 662.11) (253.67, 671.42) (027.00, 670.92)       /TT2 ¥ Vous avez acheté les produits dans une province 	<|special_separator|>
+(027.00, 676.61) (184.20, 677.11) (184.20, 686.42) (027.00, 685.92)       /TT2 • Vous êtes un résident du Canada.	<|special_separator|>
+(027.00, 661.61) (253.67, 662.11) (253.67, 671.42) (027.00, 670.92)       /TT2 • Vous avez acheté les produits dans une province 	<|special_separator|>
 (033.00, 651.11) (277.55, 651.11) (277.55, 660.42) (033.00, 660.42)       /TT2 participante et vous avez payé la TVH sur ces produits.	<|special_separator|>
-(027.00, 634.61) (280.88, 635.11) (280.88, 644.42) (027.00, 643.92)       /TT2 ¥ Vous avez acheté les produits pour les consommer, les 	<|special_separator|>
+(027.00, 634.61) (280.88, 635.11) (280.88, 644.42) (027.00, 643.92)       /TT2 • Vous avez acheté les produits pour les consommer, les 	<|special_separator|>
 (033.00, 624.11) (292.54, 624.11) (292.54, 633.42) (033.00, 633.42)       /TT2 utiliser ou les fournir exclusivement (généralement à 90 % 	<|special_separator|>
 (033.00, 613.11) (245.00, 613.11) (245.00, 622.42) (033.00, 622.42)       /TT2 ou plus) à l'extérieur de la province participante.	<|special_separator|>
-(027.00, 598.61) (246.12, 599.11) (246.12, 608.42) (027.00, 607.92)       /TT2 ¥ Vous avez transféré les produits d'une province 	<|special_separator|>
+(027.00, 598.61) (246.12, 599.11) (246.12, 608.42) (027.00, 607.92)       /TT2 • Vous avez transféré les produits d'une province 	<|special_separator|>
 (033.00, 588.11) (280.92, 588.11) (280.92, 597.42) (033.00, 597.42)       /TT2 participante dans une autre province ou dans une autre 	<|special_separator|>
 (033.00, 577.11) (287.02, 577.11) (287.02, 586.42) (033.00, 586.42)       /TT2 région du Canada dans les 30 jours suivant la date où ils 	<|special_separator|>
 (033.00, 566.11) (299.25, 566.11) (299.25, 575.42) (033.00, 575.42)       /TT2 vous ont été livrés (toute période pendant laquelle les biens 	<|special_separator|>
 (033.00, 555.11) (294.81, 555.11) (294.81, 564.42) (033.00, 564.42)       /TT2 étaient entreposés dans la province participante avant que 	<|special_separator|>
 (033.00, 544.11) (284.46, 544.11) (284.46, 553.42) (033.00, 553.42)       /TT2 vous ne les retiriez n'est pas comptée dans les 30 jours).	<|special_separator|>
-(027.00, 529.61) (282.00, 530.11) (282.00, 539.42) (027.00, 538.92)       /TT2 ¥ Vous avez payé les taxes provinciales applicables de la 	<|special_separator|>
+(027.00, 529.61) (282.00, 530.11) (282.00, 539.42) (027.00, 538.92)       /TT2 • Vous avez payé les taxes provinciales applicables de la 	<|special_separator|>
 (033.00, 519.11) (287.27, 519.11) (287.27, 528.42) (033.00, 528.42)       /TT2 province non participante ou de l'autre région du Canada 	<|special_separator|>
 (033.00, 508.11) (181.41, 508.11) (181.41, 517.42) (033.00, 517.42)       /TT2 où les produits ont été transférés.	<|special_separator|>
-(027.00, 493.61) (249.21, 494.58) (249.21, 503.89) (027.00, 502.92)       /TT2 ¥ Si vous êtes un consommateur du bien (sauf les 	<|special_separator|>
+(027.00, 493.61) (249.21, 494.58) (249.21, 503.89) (027.00, 502.92)       /TT2 • Si vous êtes un consommateur du bien (sauf les 	<|special_separator|>
 (249.21, 494.57) (297.57, 494.57) (297.57, 503.92) (249.21, 503.92)       /TT1 véhicules 	<|special_separator|>
 (033.00, 483.57) (131.36, 483.57) (131.36, 492.92) (033.00, 492.92)       /TT1 à moteur déterminés	<|special_separator|>
 (131.36, 483.58) (288.65, 483.58) (288.65, 492.89) (131.36, 492.89)       /TT2 ), vous résidez dans la province ou 	<|special_separator|>
 (033.00, 472.58) (281.47, 472.58) (281.47, 481.89) (033.00, 481.89)       /TT2 autre région du Canada où vous avez apporté les biens.	<|special_separator|>
-(027.00, 457.61) (030.50, 457.61) (030.50, 466.92) (027.00, 466.92)       /TT2 ¥	<|special_separator|>
+(027.00, 457.61) (030.50, 457.61) (030.50, 466.92) (027.00, 466.92)       /TT2 •	<|special_separator|>
 (033.00, 458.57) (093.57, 458.57) (093.57, 467.92) (033.00, 467.92)       /TT1 Chaque reçu	<|special_separator|>
 (093.57, 458.58) (273.65, 458.58) (273.65, 467.89) (093.57, 467.89)       /TT2  indique un montant minimum de la taxe 	<|special_separator|>
 (033.00, 447.58) (113.59, 447.58) (113.59, 456.89) (033.00, 456.89)       /TT2 admissible de 5 $.	<|special_separator|>
-(027.00, 430.61) (030.50, 430.61) (030.50, 439.92) (027.00, 439.92)       /TT2 ¥	<|special_separator|>
+(027.00, 430.61) (030.50, 430.61) (030.50, 439.92) (027.00, 439.92)       /TT2 •	<|special_separator|>
 (033.00, 431.57) (206.91, 431.57) (206.91, 440.92) (033.00, 440.92)       /TT1 Le montant total du remboursement 	<|special_separator|>
 (206.91, 431.58) (253.05, 431.58) (253.05, 440.89) (206.91, 440.89)       /TT2 de la taxe 	<|special_separator|>
 (033.00, 420.58) (170.29, 420.58) (170.29, 429.89) (033.00, 429.89)       /TT2 admissible est de 25 $ ou plus.	<|special_separator|>
@@ -59,11 +59,11 @@
 (021.00, 262.14) (220.28, 262.14) (220.28, 272.43) (021.00, 272.43)       /TT1 Documents à joindre à votre demande	<|special_separator|>
 (021.00, 248.11) (283.34, 248.11) (283.34, 257.42) (021.00, 257.42)       /TT2 Joignez les renseignements et documents suivants à votre 	<|special_separator|>
 (021.00, 237.11) (068.25, 237.11) (068.25, 246.42) (021.00, 246.42)       /TT2 demande :	<|special_separator|>
-(027.00, 217.61) (211.98, 218.11) (211.98, 227.42) (027.00, 226.92)       /TT2 ¥ les copies des reçus pour chaque achat;	<|special_separator|>
-(027.00, 202.61) (288.67, 203.11) (288.67, 212.42) (027.00, 211.92)       /TT2 ¥ la preuve de paiement des taxes provinciales applicables;	<|special_separator|>
-(027.00, 187.61) (274.77, 188.11) (274.77, 197.42) (027.00, 196.92)       /TT2 ¥ si le produit admissible était entreposé, les copies des 	<|special_separator|>
+(027.00, 217.61) (211.98, 218.11) (211.98, 227.42) (027.00, 226.92)       /TT2 • les copies des reçus pour chaque achat;	<|special_separator|>
+(027.00, 202.61) (288.67, 203.11) (288.67, 212.42) (027.00, 211.92)       /TT2 • la preuve de paiement des taxes provinciales applicables;	<|special_separator|>
+(027.00, 187.61) (274.77, 188.11) (274.77, 197.42) (027.00, 196.92)       /TT2 • si le produit admissible était entreposé, les copies des 	<|special_separator|>
 (033.00, 177.11) (236.68, 177.11) (236.68, 186.42) (033.00, 186.42)       /TT2 reçus afin de justifier la date de l'entreposage.	<|special_separator|>
-(027.00, 160.61) (268.91, 161.11) (268.91, 170.42) (027.00, 169.92)       /TT2 ¥ dans le cas d'un véhicule à moteur déterminé qui est 	<|special_separator|>
+(027.00, 160.61) (268.91, 161.11) (268.91, 170.42) (027.00, 169.92)       /TT2 • dans le cas d'un véhicule à moteur déterminé qui est 	<|special_separator|>
 (033.00, 150.11) (234.20, 150.11) (234.20, 159.42) (033.00, 159.42)       /TT2 immatriculé dans une province, une copie de 	<|special_separator|>
 (033.00, 139.11) (287.23, 139.11) (287.23, 148.42) (033.00, 148.42)       /TT2 l'immatriculation du véhicule de la province dans laquelle 	<|special_separator|>
 (033.00, 128.11) (143.61, 128.11) (143.61, 137.42) (033.00, 137.42)       /TT2 le véhicule a été introduit	<|special_separator|>
@@ -97,7 +97,7 @@
 (315.00, 532.14) (472.72, 532.14) (472.72, 542.43) (315.00, 542.43)       /TT1 Remplir ce formulaire en ligne	<|special_separator|>
 (315.00, 518.58) (580.11, 518.58) (580.11, 527.89) (315.00, 527.89)       /TT2 Si vous êtes un inscrit à la TPS/TVH, vous pouvez produire 	<|special_separator|>
 (315.00, 507.58) (570.12, 507.58) (570.12, 516.89) (315.00, 516.89)       /TT2 votre demande de remboursement en ligne en utilisant le 	<|special_separator|>
-(315.00, 496.58) (575.10, 496.58) (575.10, 505.89) (315.00, 505.89)       /TT2 service ˙ Produire un remboursement ¨ dans Mon dossier 	<|special_separator|>
+(315.00, 496.58) (575.10, 496.58) (575.10, 505.89) (315.00, 505.89)       /TT2 service « Produire un remboursement » dans Mon dossier 	<|special_separator|>
 (315.00, 485.58) (378.05, 485.58) (378.05, 494.89) (315.00, 494.89)       /TT2 d'entreprise à 	<|special_separator|>
 (378.05, 485.57) (559.22, 485.57) (559.22, 494.92) (378.05, 494.92)       /TT1 canada.ca/mon-dossier-entreprise-arc	<|special_separator|>
 (559.22, 485.58) (575.90, 485.58) (575.90, 494.89) (559.22, 494.89)       /TT2  ou 	<|special_separator|>
diff --git a/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json.word.txt b/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json.word.txt
index 1d1e73ce..fe4bd621 100644
--- a/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json.word.txt
+++ b/tests/data/groundtruth/form_fields.pdf.page_no_5.py.json.word.txt
@@ -31,14 +31,14 @@
 (232.19, 694.58) (251.09, 694.58) (251.09, 703.89) (232.19, 703.89)       /TT2 sont	<|special_separator|>
 (253.87, 694.58) (291.65, 694.58) (291.65, 703.89) (253.87, 703.89)       /TT2 remplies	<|special_separator|>
 (294.43, 694.58) (297.21, 694.58) (297.21, 703.89) (294.43, 703.89)       /TT2 :	<|special_separator|>
-(027.00, 676.61) (030.50, 676.61) (030.50, 685.92) (027.00, 685.92)       /TT2 ¥	<|special_separator|>
+(027.00, 676.61) (030.50, 676.61) (030.50, 685.92) (027.00, 685.92)       /TT2 •	<|special_separator|>
 (033.00, 677.11) (055.79, 677.11) (055.79, 686.42) (033.00, 686.42)       /TT2 Vous	<|special_separator|>
 (058.57, 677.11) (077.47, 677.11) (077.47, 686.42) (058.57, 686.42)       /TT2 êtes	<|special_separator|>
 (080.25, 677.11) (091.37, 677.11) (091.37, 686.42) (080.25, 686.42)       /TT2 un	<|special_separator|>
 (094.15, 677.11) (129.72, 677.11) (129.72, 686.42) (094.15, 686.42)       /TT2 résident	<|special_separator|>
 (132.50, 677.11) (143.62, 677.11) (143.62, 686.42) (132.50, 686.42)       /TT2 du	<|special_separator|>
 (146.40, 677.11) (184.20, 677.11) (184.20, 686.42) (146.40, 686.42)       /TT2 Canada.	<|special_separator|>
-(027.00, 661.61) (030.50, 661.61) (030.50, 670.92) (027.00, 670.92)       /TT2 ¥	<|special_separator|>
+(027.00, 661.61) (030.50, 661.61) (030.50, 670.92) (027.00, 670.92)       /TT2 •	<|special_separator|>
 (033.00, 662.11) (055.79, 662.11) (055.79, 671.42) (033.00, 671.42)       /TT2 Vous	<|special_separator|>
 (058.57, 662.11) (079.69, 662.11) (079.69, 671.42) (058.57, 671.42)       /TT2 avez	<|special_separator|>
 (082.47, 662.11) (112.49, 662.11) (112.49, 671.42) (082.47, 671.42)       /TT2 acheté	<|special_separator|>
@@ -57,7 +57,7 @@
 (204.19, 651.11) (218.08, 651.11) (218.08, 660.42) (204.19, 660.42)       /TT2 sur	<|special_separator|>
 (220.86, 651.11) (236.42, 651.11) (236.42, 660.42) (220.86, 660.42)       /TT2 ces	<|special_separator|>
 (239.20, 651.11) (277.55, 651.11) (277.55, 660.42) (239.20, 660.42)       /TT2 produits.	<|special_separator|>
-(027.00, 634.61) (030.50, 634.61) (030.50, 643.92) (027.00, 643.92)       /TT2 ¥	<|special_separator|>
+(027.00, 634.61) (030.50, 634.61) (030.50, 643.92) (027.00, 643.92)       /TT2 •	<|special_separator|>
 (033.00, 635.11) (055.79, 635.11) (055.79, 644.42) (033.00, 644.42)       /TT2 Vous	<|special_separator|>
 (058.57, 635.11) (079.69, 635.11) (079.69, 644.42) (058.57, 644.42)       /TT2 avez	<|special_separator|>
 (082.47, 635.11) (112.49, 635.11) (112.49, 644.42) (082.47, 644.42)       /TT2 acheté	<|special_separator|>
@@ -83,7 +83,7 @@
 (139.40, 613.11) (147.18, 613.11) (147.18, 622.42) (139.40, 622.42)       /TT2 la	<|special_separator|>
 (149.96, 613.11) (187.75, 613.11) (187.75, 622.42) (149.96, 622.42)       /TT2 province	<|special_separator|>
 (190.53, 613.11) (245.00, 613.11) (245.00, 622.42) (190.53, 622.42)       /TT2 participante.	<|special_separator|>
-(027.00, 598.61) (030.50, 598.61) (030.50, 607.92) (027.00, 607.92)       /TT2 ¥	<|special_separator|>
+(027.00, 598.61) (030.50, 598.61) (030.50, 607.92) (027.00, 607.92)       /TT2 •	<|special_separator|>
 (033.00, 599.11) (055.79, 599.11) (055.79, 608.42) (033.00, 608.42)       /TT2 Vous	<|special_separator|>
 (058.57, 599.11) (079.69, 599.11) (079.69, 608.42) (058.57, 608.42)       /TT2 avez	<|special_separator|>
 (082.47, 599.11) (121.93, 599.11) (121.93, 608.42) (082.47, 608.42)       /TT2 transféré	<|special_separator|>
@@ -141,7 +141,7 @@
 (227.22, 544.11) (240.00, 544.11) (240.00, 553.42) (227.22, 553.42)       /TT2 les	<|special_separator|>
 (242.78, 544.11) (253.90, 544.11) (253.90, 553.42) (242.78, 553.42)       /TT2 30	<|special_separator|>
 (256.68, 544.11) (284.46, 544.11) (284.46, 553.42) (256.68, 553.42)       /TT2 jours).	<|special_separator|>
-(027.00, 529.61) (030.50, 529.61) (030.50, 538.92) (027.00, 538.92)       /TT2 ¥	<|special_separator|>
+(027.00, 529.61) (030.50, 529.61) (030.50, 538.92) (027.00, 538.92)       /TT2 •	<|special_separator|>
 (033.00, 530.11) (055.79, 530.11) (055.79, 539.42) (033.00, 539.42)       /TT2 Vous	<|special_separator|>
 (058.57, 530.11) (079.69, 530.11) (079.69, 539.42) (058.57, 539.42)       /TT2 avez	<|special_separator|>
 (082.47, 530.11) (104.15, 530.11) (104.15, 539.42) (082.47, 539.42)       /TT2 payé	<|special_separator|>
@@ -166,7 +166,7 @@
 (100.81, 508.11) (114.71, 508.11) (114.71, 517.42) (100.81, 517.42)       /TT2 ont	<|special_separator|>
 (117.49, 508.11) (131.39, 508.11) (131.39, 517.42) (117.49, 517.42)       /TT2 été	<|special_separator|>
 (134.17, 508.11) (181.41, 508.11) (181.41, 517.42) (134.17, 517.42)       /TT2 transférés.	<|special_separator|>
-(027.00, 493.61) (030.50, 493.61) (030.50, 502.92) (027.00, 502.92)       /TT2 ¥	<|special_separator|>
+(027.00, 493.61) (030.50, 493.61) (030.50, 502.92) (027.00, 502.92)       /TT2 •	<|special_separator|>
 (033.00, 494.58) (041.89, 494.58) (041.89, 503.89) (033.00, 503.89)       /TT2 Si	<|special_separator|>
 (044.67, 494.58) (065.79, 494.58) (065.79, 503.89) (044.67, 503.89)       /TT2 vous	<|special_separator|>
 (068.57, 494.58) (087.47, 494.58) (087.47, 503.89) (068.57, 503.89)       /TT2 êtes	<|special_separator|>
@@ -197,7 +197,7 @@
 (202.54, 472.58) (236.45, 472.58) (236.45, 481.89) (202.54, 481.89)       /TT2 apporté	<|special_separator|>
 (239.23, 472.58) (252.01, 472.58) (252.01, 481.89) (239.23, 481.89)       /TT2 les	<|special_separator|>
 (254.79, 472.58) (281.47, 472.58) (281.47, 481.89) (254.79, 481.89)       /TT2 biens.	<|special_separator|>
-(027.00, 457.61) (030.50, 457.61) (030.50, 466.92) (027.00, 466.92)       /TT2 ¥	<|special_separator|>
+(027.00, 457.61) (030.50, 457.61) (030.50, 466.92) (027.00, 466.92)       /TT2 •	<|special_separator|>
 (033.00, 458.57) (069.67, 458.57) (069.67, 467.92) (033.00, 467.92)       /TT1 Chaque	<|special_separator|>
 (072.45, 458.57) (093.57, 458.57) (093.57, 467.92) (072.45, 467.92)       /TT1 reçu	<|special_separator|>
 (096.35, 458.58) (128.59, 458.58) (128.59, 467.89) (096.35, 467.89)       /TT2 indique	<|special_separator|>
@@ -211,7 +211,7 @@
 (083.01, 447.58) (094.13, 447.58) (094.13, 456.89) (083.01, 456.89)       /TT2 de	<|special_separator|>
 (096.91, 447.58) (102.47, 447.58) (102.47, 456.89) (096.91, 456.89)       /TT2 5	<|special_separator|>
 (105.25, 447.58) (113.59, 447.58) (113.59, 456.89) (105.25, 456.89)       /TT2 $.	<|special_separator|>
-(027.00, 430.61) (030.50, 430.61) (030.50, 439.92) (027.00, 439.92)       /TT2 ¥	<|special_separator|>
+(027.00, 430.61) (030.50, 430.61) (030.50, 439.92) (027.00, 439.92)       /TT2 •	<|special_separator|>
 (033.00, 431.57) (044.67, 431.57) (044.67, 440.92) (033.00, 440.92)       /TT1 Le	<|special_separator|>
 (047.45, 431.57) (086.89, 431.57) (086.89, 440.92) (047.45, 440.92)       /TT1 montant	<|special_separator|>
 (089.67, 431.57) (110.78, 431.57) (110.78, 440.92) (089.67, 440.92)       /TT1 total	<|special_separator|>
@@ -341,7 +341,7 @@
 (258.33, 248.11) (280.56, 248.11) (280.56, 257.42) (258.33, 257.42)       /TT2 votre	<|special_separator|>
 (021.00, 237.11) (062.69, 237.11) (062.69, 246.42) (021.00, 246.42)       /TT2 demande	<|special_separator|>
 (065.47, 237.11) (068.25, 237.11) (068.25, 246.42) (065.47, 246.42)       /TT2 :	<|special_separator|>
-(027.00, 217.61) (030.50, 217.61) (030.50, 226.92) (027.00, 226.92)       /TT2 ¥	<|special_separator|>
+(027.00, 217.61) (030.50, 217.61) (030.50, 226.92) (027.00, 226.92)       /TT2 •	<|special_separator|>
 (033.00, 218.11) (045.78, 218.11) (045.78, 227.42) (033.00, 227.42)       /TT2 les	<|special_separator|>
 (048.56, 218.11) (077.46, 218.11) (077.46, 227.42) (048.56, 227.42)       /TT2 copies	<|special_separator|>
 (080.24, 218.11) (096.36, 218.11) (096.36, 227.42) (080.24, 227.42)       /TT2 des	<|special_separator|>
@@ -349,7 +349,7 @@
 (126.37, 218.11) (146.38, 218.11) (146.38, 227.42) (126.37, 227.42)       /TT2 pour	<|special_separator|>
 (149.16, 218.11) (181.96, 218.11) (181.96, 227.42) (149.16, 227.42)       /TT2 chaque	<|special_separator|>
 (184.74, 218.11) (211.98, 218.11) (211.98, 227.42) (184.74, 227.42)       /TT2 achat;	<|special_separator|>
-(027.00, 202.61) (030.50, 202.61) (030.50, 211.92) (027.00, 211.92)       /TT2 ¥	<|special_separator|>
+(027.00, 202.61) (030.50, 202.61) (030.50, 211.92) (027.00, 211.92)       /TT2 •	<|special_separator|>
 (033.00, 203.11) (040.78, 203.11) (040.78, 212.42) (033.00, 212.42)       /TT2 la	<|special_separator|>
 (043.56, 203.11) (074.13, 203.11) (074.13, 212.42) (043.56, 212.42)       /TT2 preuve	<|special_separator|>
 (076.91, 203.11) (088.03, 203.11) (088.03, 212.42) (076.91, 212.42)       /TT2 de	<|special_separator|>
@@ -358,7 +358,7 @@
 (153.62, 203.11) (177.52, 203.11) (177.52, 212.42) (153.62, 212.42)       /TT2 taxes	<|special_separator|>
 (180.30, 203.11) (233.09, 203.11) (233.09, 212.42) (180.30, 212.42)       /TT2 provinciales	<|special_separator|>
 (235.87, 203.11) (288.67, 203.11) (288.67, 212.42) (235.87, 212.42)       /TT2 applicables;	<|special_separator|>
-(027.00, 187.61) (030.50, 187.61) (030.50, 196.92) (027.00, 196.92)       /TT2 ¥	<|special_separator|>
+(027.00, 187.61) (030.50, 187.61) (030.50, 196.92) (027.00, 196.92)       /TT2 •	<|special_separator|>
 (033.00, 188.11) (040.22, 188.11) (040.22, 197.42) (033.00, 197.42)       /TT2 si	<|special_separator|>
 (043.00, 188.11) (050.78, 188.11) (050.78, 197.42) (043.00, 197.42)       /TT2 le	<|special_separator|>
 (053.56, 188.11) (084.13, 188.11) (084.13, 197.42) (053.56, 197.42)       /TT2 produit	<|special_separator|>
@@ -376,7 +376,7 @@
 (138.04, 177.11) (157.50, 177.11) (157.50, 186.42) (138.04, 186.42)       /TT2 date	<|special_separator|>
 (160.28, 177.11) (171.40, 177.11) (171.40, 186.42) (160.28, 186.42)       /TT2 de	<|special_separator|>
 (174.18, 177.11) (236.68, 177.11) (236.68, 186.42) (174.18, 186.42)       /TT2 l'entreposage.	<|special_separator|>
-(027.00, 160.61) (030.50, 160.61) (030.50, 169.92) (027.00, 169.92)       /TT2 ¥	<|special_separator|>
+(027.00, 160.61) (030.50, 160.61) (030.50, 169.92) (027.00, 169.92)       /TT2 •	<|special_separator|>
 (033.00, 161.11) (054.68, 161.11) (054.68, 170.42) (033.00, 170.42)       /TT2 dans	<|special_separator|>
 (057.46, 161.11) (065.24, 161.11) (065.24, 170.42) (057.46, 170.42)       /TT2 le	<|special_separator|>
 (068.02, 161.11) (083.58, 161.11) (083.58, 170.42) (068.02, 170.42)       /TT2 cas	<|special_separator|>
@@ -581,11 +581,11 @@
 (522.88, 507.58) (556.78, 507.58) (556.78, 516.89) (522.88, 516.89)       /TT2 utilisant	<|special_separator|>
 (559.56, 507.58) (567.34, 507.58) (567.34, 516.89) (559.56, 516.89)       /TT2 le	<|special_separator|>
 (315.00, 496.58) (346.67, 496.58) (346.67, 505.89) (315.00, 505.89)       /TT2 service	<|special_separator|>
-(349.45, 496.58) (355.01, 496.58) (355.01, 505.89) (349.45, 505.89)       /TT2 ˙	<|special_separator|>
+(349.45, 496.58) (355.01, 496.58) (355.01, 505.89) (349.45, 505.89)       /TT2 «	<|special_separator|>
 (357.79, 496.58) (395.58, 496.58) (395.58, 505.89) (357.79, 505.89)       /TT2 Produire	<|special_separator|>
 (398.36, 496.58) (409.48, 496.58) (409.48, 505.89) (398.36, 505.89)       /TT2 un	<|special_separator|>
 (412.26, 496.58) (482.28, 496.58) (482.28, 505.89) (412.26, 505.89)       /TT2 remboursement	<|special_separator|>
-(485.06, 496.58) (490.62, 496.58) (490.62, 505.89) (485.06, 505.89)       /TT2 ¨	<|special_separator|>
+(485.06, 496.58) (490.62, 496.58) (490.62, 505.89) (485.06, 505.89)       /TT2 »	<|special_separator|>
 (493.40, 496.58) (515.08, 496.58) (515.08, 505.89) (493.40, 505.89)       /TT2 dans	<|special_separator|>
 (517.86, 496.58) (537.31, 496.58) (537.31, 505.89) (517.86, 505.89)       /TT2 Mon	<|special_separator|>
 (540.09, 496.58) (572.32, 496.58) (572.32, 505.89) (540.09, 505.89)       /TT2 dossier	<|special_separator|>
diff --git a/tests/data/groundtruth/form_fields.pdf.v2.json b/tests/data/groundtruth/form_fields.pdf.v2.json
index 779ab069..4a735d00 100644
--- a/tests/data/groundtruth/form_fields.pdf.v2.json
+++ b/tests/data/groundtruth/form_fields.pdf.v2.json
@@ -8171,7 +8171,7 @@
               661.42,
               28.459,
               661.42,
-              "\u00ba",
+              "\u00ce",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -33862,7 +33862,7 @@
               251.389,
               42.218,
               251.389,
-              "\u00a1",
+              "\u00b0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -34161,7 +34161,7 @@
               251.389,
               94.828,
               251.389,
-              "\u00a1",
+              "\u00b0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -36024,7 +36024,7 @@
               103.42,
               22.999,
               103.42,
-              "\u00b8",
+              "\u00c0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -39392,7 +39392,7 @@
               661.42,
               20.999,
               661.42,
-              "(l'\u00bale-du-Prince-\u00c9douard, le Nouveau-Brunswick, la Nouvelle-\u00c9cosse, l'Ontario ou  ",
+              "(l'\u00cele-du-Prince-\u00c9douard, le Nouveau-Brunswick, la Nouvelle-\u00c9cosse, l'Ontario ou  ",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -40013,7 +40013,7 @@
               251.389,
               34.998,
               251.389,
-              "N\u00a1 d'unit\u00e9 - n\u00a1 et rue, CP, RR :",
+              "N\u00b0 d'unit\u00e9 - n\u00b0 et rue, CP, RR :",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -40128,7 +40128,7 @@
               103.42,
               22.999,
               103.42,
-              "\u00b8 USAGE INTERNE",
+              "\u00c0 USAGE INTERNE",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -45001,7 +45001,7 @@
               698.39,
               42.218,
               698.39,
-              "\u00a1",
+              "\u00b0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -45300,7 +45300,7 @@
               698.39,
               94.828,
               698.39,
-              "\u00a1",
+              "\u00b0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -67201,7 +67201,7 @@
               698.39,
               34.998,
               698.39,
-              "N\u00a1 d'unit\u00e9 - n\u00a1 et rue, RR :",
+              "N\u00b0 d'unit\u00e9 - n\u00b0 et rue, RR :",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -171413,7 +171413,7 @@
               685.918,
               26.999,
               685.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -172172,7 +172172,7 @@
               670.918,
               26.999,
               670.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -174564,7 +174564,7 @@
               643.918,
               26.999,
               643.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -178359,7 +178359,7 @@
               607.918,
               26.999,
               607.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -186202,7 +186202,7 @@
               538.918,
               26.999,
               538.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -189629,7 +189629,7 @@
               502.918,
               26.999,
               502.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -193470,7 +193470,7 @@
               466.918,
               26.999,
               466.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -195057,7 +195057,7 @@
               439.918,
               26.999,
               439.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -213641,7 +213641,7 @@
               226.918,
               26.999,
               226.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -214561,7 +214561,7 @@
               211.918,
               26.999,
               211.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -215895,7 +215895,7 @@
               196.918,
               26.999,
               196.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -218356,7 +218356,7 @@
               169.918,
               26.999,
               169.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -248095,7 +248095,7 @@
               505.888,
               349.45,
               505.888,
-              "\u02d9",
+              "\u00ab",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -248739,7 +248739,7 @@
               505.888,
               485.06,
               505.888,
-              "\u00a8",
+              "\u00bb",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -274723,7 +274723,7 @@
               686.418,
               26.999,
               685.918,
-              "\u00a5 Vous \u00eates un r\u00e9sident du Canada.",
+              "\u2022 Vous \u00eates un r\u00e9sident du Canada.",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -274746,7 +274746,7 @@
               671.418,
               26.999,
               670.918,
-              "\u00a5 Vous avez achet\u00e9 les produits dans une province ",
+              "\u2022 Vous avez achet\u00e9 les produits dans une province ",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -274792,7 +274792,7 @@
               644.418,
               26.999,
               643.918,
-              "\u00a5 Vous avez achet\u00e9 les produits pour les consommer, les ",
+              "\u2022 Vous avez achet\u00e9 les produits pour les consommer, les ",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -274861,7 +274861,7 @@
               608.418,
               26.999,
               607.918,
-              "\u00a5 Vous avez transf\u00e9r\u00e9 les produits d'une province ",
+              "\u2022 Vous avez transf\u00e9r\u00e9 les produits d'une province ",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -274999,7 +274999,7 @@
               539.418,
               26.999,
               538.918,
-              "\u00a5 Vous avez pay\u00e9 les taxes provinciales applicables de la ",
+              "\u2022 Vous avez pay\u00e9 les taxes provinciales applicables de la ",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -275068,7 +275068,7 @@
               503.888,
               26.999,
               502.918,
-              "\u00a5 Si vous \u00eates un consommateur du bien (sauf les ",
+              "\u2022 Si vous \u00eates un consommateur du bien (sauf les ",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -275183,7 +275183,7 @@
               466.918,
               26.999,
               466.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -275275,7 +275275,7 @@
               439.918,
               26.999,
               439.918,
-              "\u00a5",
+              "\u2022",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -275919,7 +275919,7 @@
               227.418,
               26.999,
               226.918,
-              "\u00a5 les copies des re\u00e7us pour chaque achat;",
+              "\u2022 les copies des re\u00e7us pour chaque achat;",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -275942,7 +275942,7 @@
               212.418,
               26.999,
               211.918,
-              "\u00a5 la preuve de paiement des taxes provinciales applicables;",
+              "\u2022 la preuve de paiement des taxes provinciales applicables;",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -275965,7 +275965,7 @@
               197.418,
               26.999,
               196.918,
-              "\u00a5 si le produit admissible \u00e9tait entrepos\u00e9, les copies des ",
+              "\u2022 si le produit admissible \u00e9tait entrepos\u00e9, les copies des ",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -276011,7 +276011,7 @@
               170.418,
               26.999,
               169.918,
-              "\u00a5 dans le cas d'un v\u00e9hicule \u00e0 moteur d\u00e9termin\u00e9 qui est ",
+              "\u2022 dans le cas d'un v\u00e9hicule \u00e0 moteur d\u00e9termin\u00e9 qui est ",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -276793,7 +276793,7 @@
               505.888,
               315.0,
               505.888,
-              "service \u02d9 Produire un remboursement \u00a8 dans Mon dossier ",
+              "service \u00ab Produire un remboursement \u00bb dans Mon dossier ",
               -1,
               2.78,
               "/MacRomanEncoding",
diff --git a/tests/data/groundtruth/form_fields.pdf.v2.p=0.json b/tests/data/groundtruth/form_fields.pdf.v2.p=0.json
index 4cfd466f..cc1b11b1 100644
--- a/tests/data/groundtruth/form_fields.pdf.v2.p=0.json
+++ b/tests/data/groundtruth/form_fields.pdf.v2.p=0.json
@@ -8171,7 +8171,7 @@
               661.42,
               28.459,
               661.42,
-              "\u00ba",
+              "\u00ce",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -33862,7 +33862,7 @@
               251.389,
               42.218,
               251.389,
-              "\u00a1",
+              "\u00b0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -34161,7 +34161,7 @@
               251.389,
               94.828,
               251.389,
-              "\u00a1",
+              "\u00b0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -36024,7 +36024,7 @@
               103.42,
               22.999,
               103.42,
-              "\u00b8",
+              "\u00c0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -38279,7 +38279,7 @@
               661.42,
               20.999,
               661.42,
-              "(l'\u00bale-du-Prince-\u00c9douard, le Nouveau-Brunswick, la Nouvelle-\u00c9cosse, l'Ontario ou  ",
+              "(l'\u00cele-du-Prince-\u00c9douard, le Nouveau-Brunswick, la Nouvelle-\u00c9cosse, l'Ontario ou  ",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -38900,7 +38900,7 @@
               251.389,
               34.998,
               251.389,
-              "N\u00a1 d'unit\u00e9 - n\u00a1 et rue, CP, RR :",
+              "N\u00b0 d'unit\u00e9 - n\u00b0 et rue, CP, RR :",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -39015,7 +39015,7 @@
               103.42,
               22.999,
               103.42,
-              "\u00b8 USAGE INTERNE",
+              "\u00c0 USAGE INTERNE",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -41509,7 +41509,7 @@
               661.42,
               20.999,
               661.42,
-              "(l'\u00bale-du-Prince-\u00c9douard,",
+              "(l'\u00cele-du-Prince-\u00c9douard,",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -45281,7 +45281,7 @@
               251.389,
               34.998,
               251.389,
-              "N\u00a1",
+              "N\u00b0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -45350,7 +45350,7 @@
               251.389,
               89.268,
               251.389,
-              "n\u00a1",
+              "n\u00b0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -45810,7 +45810,7 @@
               103.42,
               22.999,
               103.42,
-              "\u00b8",
+              "\u00c0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -46553,7 +46553,7 @@
               661.42,
               20.999,
               661.42,
-              "(l'\u00bale-du-Prince-\u00c9douard, le Nouveau-Brunswick, la Nouvelle-\u00c9cosse, l'Ontario ou  ",
+              "(l'\u00cele-du-Prince-\u00c9douard, le Nouveau-Brunswick, la Nouvelle-\u00c9cosse, l'Ontario ou  ",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -47174,7 +47174,7 @@
               251.389,
               34.998,
               251.389,
-              "N\u00a1 d'unit\u00e9 - n\u00a1 et rue, CP, RR :",
+              "N\u00b0 d'unit\u00e9 - n\u00b0 et rue, CP, RR :",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -47289,7 +47289,7 @@
               103.42,
               22.999,
               103.42,
-              "\u00b8 USAGE INTERNE",
+              "\u00c0 USAGE INTERNE",
               -1,
               2.78,
               "/MacRomanEncoding",
diff --git a/tests/data/groundtruth/form_fields.pdf.v2.p=1.json b/tests/data/groundtruth/form_fields.pdf.v2.p=1.json
index 42c09a0b..5d4348e6 100644
--- a/tests/data/groundtruth/form_fields.pdf.v2.p=1.json
+++ b/tests/data/groundtruth/form_fields.pdf.v2.p=1.json
@@ -3743,7 +3743,7 @@
               698.39,
               42.218,
               698.39,
-              "\u00a1",
+              "\u00b0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -4042,7 +4042,7 @@
               698.39,
               94.828,
               698.39,
-              "\u00a1",
+              "\u00b0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -25420,7 +25420,7 @@
               698.39,
               34.998,
               698.39,
-              "N\u00a1 d'unit\u00e9 - n\u00a1 et rue, RR :",
+              "N\u00b0 d'unit\u00e9 - n\u00b0 et rue, RR :",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -27025,7 +27025,7 @@
               698.39,
               34.998,
               698.39,
-              "N\u00a1",
+              "N\u00b0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -27094,7 +27094,7 @@
               698.39,
               89.268,
               698.39,
-              "n\u00a1",
+              "n\u00b0",
               -1,
               2.78,
               "/MacRomanEncoding",
@@ -30712,7 +30712,7 @@
               698.39,
               34.998,
               698.39,
-              "N\u00a1 d'unit\u00e9 - n\u00a1 et rue, RR :",
+              "N\u00b0 d'unit\u00e9 - n\u00b0 et rue, RR :",
               -1,
               2.78,
               "/MacRomanEncoding",
diff --git a/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.page_no_1.py.json b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.page_no_1.py.json
new file mode 100644
index 00000000..d9910662
--- /dev/null
+++ b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.page_no_1.py.json
@@ -0,0 +1,1513 @@
+{
+  "dimension": {
+    "angle": 0.0,
+    "rect": {
+      "r_x0": 0.0,
+      "r_y0": 0.0,
+      "r_x1": 612.0,
+      "r_y1": 0.0,
+      "r_x2": 612.0,
+      "r_y2": 792.0,
+      "r_x3": 0.0,
+      "r_y3": 792.0,
+      "coord_origin": "BOTTOMLEFT"
+    },
+    "boundary_type": "crop_box",
+    "art_bbox": {
+      "l": 0.0,
+      "t": 792.0,
+      "r": 612.0,
+      "b": 0.0,
+      "coord_origin": "BOTTOMLEFT"
+    },
+    "bleed_bbox": {
+      "l": 0.0,
+      "t": 792.0,
+      "r": 612.0,
+      "b": 0.0,
+      "coord_origin": "BOTTOMLEFT"
+    },
+    "crop_bbox": {
+      "l": 0.0,
+      "t": 792.0,
+      "r": 612.0,
+      "b": 0.0,
+      "coord_origin": "BOTTOMLEFT"
+    },
+    "media_bbox": {
+      "l": 0.0,
+      "t": 792.0,
+      "r": 612.0,
+      "b": 0.0,
+      "coord_origin": "BOTTOMLEFT"
+    },
+    "trim_bbox": {
+      "l": 0.0,
+      "t": 792.0,
+      "r": 612.0,
+      "b": 0.0,
+      "coord_origin": "BOTTOMLEFT"
+    }
+  },
+  "bitmap_resources": [],
+  "char_cells": [
+    {
+      "index": 0,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 50.0,
+        "r_y0": 697.652,
+        "r_x1": 58.554,
+        "r_y1": 697.652,
+        "r_x2": 58.554,
+        "r_y2": 710.024,
+        "r_x3": 50.0,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "T",
+      "orig": "T",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 1,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 58.554,
+        "r_y0": 697.652,
+        "r_x1": 66.338,
+        "r_y1": 697.652,
+        "r_x2": 66.338,
+        "r_y2": 710.024,
+        "r_x3": 58.554,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "e",
+      "orig": "e",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 2,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 66.338,
+        "r_y0": 697.652,
+        "r_x1": 78.0,
+        "r_y1": 697.652,
+        "r_x2": 78.0,
+        "r_y2": 710.024,
+        "r_x3": 66.338,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "m",
+      "orig": "m",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 3,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 78.0,
+        "r_y0": 697.652,
+        "r_x1": 85.784,
+        "r_y1": 697.652,
+        "r_x2": 85.784,
+        "r_y2": 710.024,
+        "r_x3": 78.0,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "p",
+      "orig": "p",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 4,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 85.784,
+        "r_y0": 697.652,
+        "r_x1": 93.568,
+        "r_y1": 697.652,
+        "r_x2": 93.568,
+        "r_y2": 710.024,
+        "r_x3": 85.784,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "e",
+      "orig": "e",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 5,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 93.568,
+        "r_y0": 697.652,
+        "r_x1": 98.23,
+        "r_y1": 697.652,
+        "r_x2": 98.23,
+        "r_y2": 710.024,
+        "r_x3": 93.568,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "r",
+      "orig": "r",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 6,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 98.23,
+        "r_y0": 697.652,
+        "r_x1": 106.014,
+        "r_y1": 697.652,
+        "r_x2": 106.014,
+        "r_y2": 710.024,
+        "r_x3": 98.23,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "a",
+      "orig": "a",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 7,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 106.014,
+        "r_y0": 697.652,
+        "r_x1": 109.906,
+        "r_y1": 697.652,
+        "r_x2": 109.906,
+        "r_y2": 710.024,
+        "r_x3": 106.014,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "t",
+      "orig": "t",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 8,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 109.906,
+        "r_y0": 697.652,
+        "r_x1": 117.69,
+        "r_y1": 697.652,
+        "r_x2": 117.69,
+        "r_y2": 710.024,
+        "r_x3": 109.906,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "u",
+      "orig": "u",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 9,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 117.69,
+        "r_y0": 697.652,
+        "r_x1": 122.352,
+        "r_y1": 697.652,
+        "r_x2": 122.352,
+        "r_y2": 710.024,
+        "r_x3": 117.69,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "r",
+      "orig": "r",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 10,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 122.352,
+        "r_y0": 697.652,
+        "r_x1": 130.136,
+        "r_y1": 697.652,
+        "r_x2": 130.136,
+        "r_y2": 710.024,
+        "r_x3": 122.352,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "e",
+      "orig": "e",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 11,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 130.136,
+        "r_y0": 697.652,
+        "r_x1": 134.028,
+        "r_y1": 697.652,
+        "r_x2": 134.028,
+        "r_y2": 710.024,
+        "r_x3": 130.136,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": ":",
+      "orig": ":",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 12,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 134.028,
+        "r_y0": 697.652,
+        "r_x1": 137.92,
+        "r_y1": 697.652,
+        "r_x2": 137.92,
+        "r_y2": 710.024,
+        "r_x3": 134.028,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": " ",
+      "orig": " ",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 13,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 137.92,
+        "r_y0": 697.652,
+        "r_x1": 145.704,
+        "r_y1": 697.652,
+        "r_x2": 145.704,
+        "r_y2": 710.024,
+        "r_x3": 137.92,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "1",
+      "orig": "1",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 14,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 145.704,
+        "r_y0": 697.652,
+        "r_x1": 153.488,
+        "r_y1": 697.652,
+        "r_x2": 153.488,
+        "r_y2": 710.024,
+        "r_x3": 145.704,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "0",
+      "orig": "0",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 15,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 153.488,
+        "r_y0": 697.652,
+        "r_x1": 161.272,
+        "r_y1": 697.652,
+        "r_x2": 161.272,
+        "r_y2": 710.024,
+        "r_x3": 153.488,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "0",
+      "orig": "0",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 16,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 161.272,
+        "r_y0": 697.652,
+        "r_x1": 166.872,
+        "r_y1": 697.652,
+        "r_x2": 166.872,
+        "r_y2": 710.024,
+        "r_x3": 161.272,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "\u00b0",
+      "orig": "\u00b0",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 17,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 166.872,
+        "r_y0": 697.652,
+        "r_x1": 175.426,
+        "r_y1": 697.652,
+        "r_x2": 175.426,
+        "r_y2": 710.024,
+        "r_x3": 166.872,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "F",
+      "orig": "F",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 18,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 50.0,
+        "r_y0": 677.652,
+        "r_x1": 59.338,
+        "r_y1": 677.652,
+        "r_x2": 59.338,
+        "r_y2": 690.024,
+        "r_x3": 50.0,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "S",
+      "orig": "S",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 19,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 59.338,
+        "r_y0": 677.652,
+        "r_x1": 67.122,
+        "r_y1": 677.652,
+        "r_x2": 67.122,
+        "r_y2": 690.024,
+        "r_x3": 59.338,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "p",
+      "orig": "p",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 20,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 67.122,
+        "r_y0": 677.652,
+        "r_x1": 74.906,
+        "r_y1": 677.652,
+        "r_x2": 74.906,
+        "r_y2": 690.024,
+        "r_x3": 67.122,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "e",
+      "orig": "e",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 21,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 74.906,
+        "r_y0": 677.652,
+        "r_x1": 81.906,
+        "r_y1": 677.652,
+        "r_x2": 81.906,
+        "r_y2": 690.024,
+        "r_x3": 74.906,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "c",
+      "orig": "c",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 22,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 81.906,
+        "r_y0": 677.652,
+        "r_x1": 85.014,
+        "r_y1": 677.652,
+        "r_x2": 85.014,
+        "r_y2": 690.024,
+        "r_x3": 81.906,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "i",
+      "orig": "i",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 23,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 85.014,
+        "r_y0": 677.652,
+        "r_x1": 88.906,
+        "r_y1": 677.652,
+        "r_x2": 88.906,
+        "r_y2": 690.024,
+        "r_x3": 85.014,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "f",
+      "orig": "f",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 24,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 88.906,
+        "r_y0": 677.652,
+        "r_x1": 92.014,
+        "r_y1": 677.652,
+        "r_x2": 92.014,
+        "r_y2": 690.024,
+        "r_x3": 88.906,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "i",
+      "orig": "i",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 25,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 92.014,
+        "r_y0": 677.652,
+        "r_x1": 99.014,
+        "r_y1": 677.652,
+        "r_x2": 99.014,
+        "r_y2": 690.024,
+        "r_x3": 92.014,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "c",
+      "orig": "c",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 26,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 99.014,
+        "r_y0": 677.652,
+        "r_x1": 102.906,
+        "r_y1": 677.652,
+        "r_x2": 102.906,
+        "r_y2": 690.024,
+        "r_x3": 99.014,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": " ",
+      "orig": " ",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 27,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 102.906,
+        "r_y0": 677.652,
+        "r_x1": 113.798,
+        "r_y1": 677.652,
+        "r_x2": 113.798,
+        "r_y2": 690.024,
+        "r_x3": 102.906,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "G",
+      "orig": "G",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 28,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 113.798,
+        "r_y0": 677.652,
+        "r_x1": 118.46,
+        "r_y1": 677.652,
+        "r_x2": 118.46,
+        "r_y2": 690.024,
+        "r_x3": 113.798,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "r",
+      "orig": "r",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 29,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 118.46,
+        "r_y0": 677.652,
+        "r_x1": 126.244,
+        "r_y1": 677.652,
+        "r_x2": 126.244,
+        "r_y2": 690.024,
+        "r_x3": 118.46,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "a",
+      "orig": "a",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 30,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 126.244,
+        "r_y0": 677.652,
+        "r_x1": 133.244,
+        "r_y1": 677.652,
+        "r_x2": 133.244,
+        "r_y2": 690.024,
+        "r_x3": 126.244,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "v",
+      "orig": "v",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 31,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 133.244,
+        "r_y0": 677.652,
+        "r_x1": 136.352,
+        "r_y1": 677.652,
+        "r_x2": 136.352,
+        "r_y2": 690.024,
+        "r_x3": 133.244,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "i",
+      "orig": "i",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 32,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 136.352,
+        "r_y0": 677.652,
+        "r_x1": 140.244,
+        "r_y1": 677.652,
+        "r_x2": 140.244,
+        "r_y2": 690.024,
+        "r_x3": 136.352,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "t",
+      "orig": "t",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 33,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 140.244,
+        "r_y0": 677.652,
+        "r_x1": 147.244,
+        "r_y1": 677.652,
+        "r_x2": 147.244,
+        "r_y2": 690.024,
+        "r_x3": 140.244,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "y",
+      "orig": "y",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 34,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 147.244,
+        "r_y0": 677.652,
+        "r_x1": 151.136,
+        "r_y1": 677.652,
+        "r_x2": 151.136,
+        "r_y2": 690.024,
+        "r_x3": 147.244,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": ":",
+      "orig": ":",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 35,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 151.136,
+        "r_y0": 677.652,
+        "r_x1": 155.028,
+        "r_y1": 677.652,
+        "r_x2": 155.028,
+        "r_y2": 690.024,
+        "r_x3": 151.136,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": " ",
+      "orig": " ",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 36,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 155.028,
+        "r_y0": 677.652,
+        "r_x1": 162.812,
+        "r_y1": 677.652,
+        "r_x2": 162.812,
+        "r_y2": 690.024,
+        "r_x3": 155.028,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "6",
+      "orig": "6",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 37,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 162.812,
+        "r_y0": 677.652,
+        "r_x1": 170.596,
+        "r_y1": 677.652,
+        "r_x2": 170.596,
+        "r_y2": 690.024,
+        "r_x3": 162.812,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "0",
+      "orig": "0",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 38,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 170.596,
+        "r_y0": 677.652,
+        "r_x1": 174.488,
+        "r_y1": 677.652,
+        "r_x2": 174.488,
+        "r_y2": 690.024,
+        "r_x3": 170.596,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "/",
+      "orig": "/",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 39,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 174.488,
+        "r_y0": 677.652,
+        "r_x1": 182.272,
+        "r_y1": 677.652,
+        "r_x2": 182.272,
+        "r_y2": 690.024,
+        "r_x3": 174.488,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "6",
+      "orig": "6",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 40,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 182.272,
+        "r_y0": 677.652,
+        "r_x1": 190.056,
+        "r_y1": 677.652,
+        "r_x2": 190.056,
+        "r_y2": 690.024,
+        "r_x3": 182.272,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "0",
+      "orig": "0",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 41,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 190.056,
+        "r_y0": 677.652,
+        "r_x1": 195.656,
+        "r_y1": 677.652,
+        "r_x2": 195.656,
+        "r_y2": 690.024,
+        "r_x3": 190.056,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "\u00b0",
+      "orig": "\u00b0",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 42,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 195.656,
+        "r_y0": 677.652,
+        "r_x1": 204.21,
+        "r_y1": 677.652,
+        "r_x2": 204.21,
+        "r_y2": 690.024,
+        "r_x3": 195.656,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "F",
+      "orig": "F",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    }
+  ],
+  "word_cells": [
+    {
+      "index": 0,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 50.0,
+        "r_y0": 697.652,
+        "r_x1": 134.028,
+        "r_y1": 697.652,
+        "r_x2": 134.028,
+        "r_y2": 710.024,
+        "r_x3": 50.0,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "Temperature:",
+      "orig": "Temperature:",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 1,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 137.92,
+        "r_y0": 697.652,
+        "r_x1": 175.426,
+        "r_y1": 697.652,
+        "r_x2": 175.426,
+        "r_y2": 710.024,
+        "r_x3": 137.92,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "100\u00b0F",
+      "orig": "100\u00b0F",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 2,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 50.0,
+        "r_y0": 677.652,
+        "r_x1": 99.014,
+        "r_y1": 677.652,
+        "r_x2": 99.014,
+        "r_y2": 690.024,
+        "r_x3": 50.0,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "Specific",
+      "orig": "Specific",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 3,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 102.906,
+        "r_y0": 677.652,
+        "r_x1": 151.136,
+        "r_y1": 677.652,
+        "r_x2": 151.136,
+        "r_y2": 690.024,
+        "r_x3": 102.906,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "Gravity:",
+      "orig": "Gravity:",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 4,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 155.028,
+        "r_y0": 677.652,
+        "r_x1": 204.21,
+        "r_y1": 677.652,
+        "r_x2": 204.21,
+        "r_y2": 690.024,
+        "r_x3": 155.028,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "60/60\u00b0F",
+      "orig": "60/60\u00b0F",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    }
+  ],
+  "textline_cells": [
+    {
+      "index": 0,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 50.0,
+        "r_y0": 697.652,
+        "r_x1": 175.426,
+        "r_y1": 697.652,
+        "r_x2": 175.426,
+        "r_y2": 710.024,
+        "r_x3": 50.0,
+        "r_y3": 710.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "Temperature: 100\u00b0F",
+      "orig": "Temperature: 100\u00b0F",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    },
+    {
+      "index": 1,
+      "rgba": {
+        "r": 0,
+        "g": 0,
+        "b": 0,
+        "a": 255
+      },
+      "rect": {
+        "r_x0": 50.0,
+        "r_y0": 677.652,
+        "r_x1": 204.21,
+        "r_y1": 677.652,
+        "r_x2": 204.21,
+        "r_y2": 690.024,
+        "r_x3": 50.0,
+        "r_y3": 690.024,
+        "coord_origin": "BOTTOMLEFT"
+      },
+      "text": "Specific Gravity: 60/60\u00b0F",
+      "orig": "Specific Gravity: 60/60\u00b0F",
+      "text_direction": "left_to_right",
+      "confidence": 1.0,
+      "from_ocr": false,
+      "rendering_mode": -1,
+      "widget": false,
+      "font_key": "/F1",
+      "font_name": "/SUBSET+ArialMT"
+    }
+  ],
+  "has_chars": true,
+  "has_words": true,
+  "has_lines": true,
+  "lines": []
+}
\ No newline at end of file
diff --git a/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.page_no_1.py.json.char.txt b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.page_no_1.py.json.char.txt
new file mode 100644
index 00000000..cea52ad1
--- /dev/null
+++ b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.page_no_1.py.json.char.txt
@@ -0,0 +1,43 @@
+(050.00, 697.65) (058.55, 697.65) (058.55, 710.02) (050.00, 710.02)        /F1 T	<|special_separator|>
+(058.55, 697.65) (066.34, 697.65) (066.34, 710.02) (058.55, 710.02)        /F1 e	<|special_separator|>
+(066.34, 697.65) (078.00, 697.65) (078.00, 710.02) (066.34, 710.02)        /F1 m	<|special_separator|>
+(078.00, 697.65) (085.78, 697.65) (085.78, 710.02) (078.00, 710.02)        /F1 p	<|special_separator|>
+(085.78, 697.65) (093.57, 697.65) (093.57, 710.02) (085.78, 710.02)        /F1 e	<|special_separator|>
+(093.57, 697.65) (098.23, 697.65) (098.23, 710.02) (093.57, 710.02)        /F1 r	<|special_separator|>
+(098.23, 697.65) (106.01, 697.65) (106.01, 710.02) (098.23, 710.02)        /F1 a	<|special_separator|>
+(106.01, 697.65) (109.91, 697.65) (109.91, 710.02) (106.01, 710.02)        /F1 t	<|special_separator|>
+(109.91, 697.65) (117.69, 697.65) (117.69, 710.02) (109.91, 710.02)        /F1 u	<|special_separator|>
+(117.69, 697.65) (122.35, 697.65) (122.35, 710.02) (117.69, 710.02)        /F1 r	<|special_separator|>
+(122.35, 697.65) (130.14, 697.65) (130.14, 710.02) (122.35, 710.02)        /F1 e	<|special_separator|>
+(130.14, 697.65) (134.03, 697.65) (134.03, 710.02) (130.14, 710.02)        /F1 :	<|special_separator|>
+(134.03, 697.65) (137.92, 697.65) (137.92, 710.02) (134.03, 710.02)        /F1  	<|special_separator|>
+(137.92, 697.65) (145.70, 697.65) (145.70, 710.02) (137.92, 710.02)        /F1 1	<|special_separator|>
+(145.70, 697.65) (153.49, 697.65) (153.49, 710.02) (145.70, 710.02)        /F1 0	<|special_separator|>
+(153.49, 697.65) (161.27, 697.65) (161.27, 710.02) (153.49, 710.02)        /F1 0	<|special_separator|>
+(161.27, 697.65) (166.87, 697.65) (166.87, 710.02) (161.27, 710.02)        /F1 °	<|special_separator|>
+(166.87, 697.65) (175.43, 697.65) (175.43, 710.02) (166.87, 710.02)        /F1 F	<|special_separator|>
+(050.00, 677.65) (059.34, 677.65) (059.34, 690.02) (050.00, 690.02)        /F1 S	<|special_separator|>
+(059.34, 677.65) (067.12, 677.65) (067.12, 690.02) (059.34, 690.02)        /F1 p	<|special_separator|>
+(067.12, 677.65) (074.91, 677.65) (074.91, 690.02) (067.12, 690.02)        /F1 e	<|special_separator|>
+(074.91, 677.65) (081.91, 677.65) (081.91, 690.02) (074.91, 690.02)        /F1 c	<|special_separator|>
+(081.91, 677.65) (085.01, 677.65) (085.01, 690.02) (081.91, 690.02)        /F1 i	<|special_separator|>
+(085.01, 677.65) (088.91, 677.65) (088.91, 690.02) (085.01, 690.02)        /F1 f	<|special_separator|>
+(088.91, 677.65) (092.01, 677.65) (092.01, 690.02) (088.91, 690.02)        /F1 i	<|special_separator|>
+(092.01, 677.65) (099.01, 677.65) (099.01, 690.02) (092.01, 690.02)        /F1 c	<|special_separator|>
+(099.01, 677.65) (102.91, 677.65) (102.91, 690.02) (099.01, 690.02)        /F1  	<|special_separator|>
+(102.91, 677.65) (113.80, 677.65) (113.80, 690.02) (102.91, 690.02)        /F1 G	<|special_separator|>
+(113.80, 677.65) (118.46, 677.65) (118.46, 690.02) (113.80, 690.02)        /F1 r	<|special_separator|>
+(118.46, 677.65) (126.24, 677.65) (126.24, 690.02) (118.46, 690.02)        /F1 a	<|special_separator|>
+(126.24, 677.65) (133.24, 677.65) (133.24, 690.02) (126.24, 690.02)        /F1 v	<|special_separator|>
+(133.24, 677.65) (136.35, 677.65) (136.35, 690.02) (133.24, 690.02)        /F1 i	<|special_separator|>
+(136.35, 677.65) (140.24, 677.65) (140.24, 690.02) (136.35, 690.02)        /F1 t	<|special_separator|>
+(140.24, 677.65) (147.24, 677.65) (147.24, 690.02) (140.24, 690.02)        /F1 y	<|special_separator|>
+(147.24, 677.65) (151.14, 677.65) (151.14, 690.02) (147.24, 690.02)        /F1 :	<|special_separator|>
+(151.14, 677.65) (155.03, 677.65) (155.03, 690.02) (151.14, 690.02)        /F1  	<|special_separator|>
+(155.03, 677.65) (162.81, 677.65) (162.81, 690.02) (155.03, 690.02)        /F1 6	<|special_separator|>
+(162.81, 677.65) (170.60, 677.65) (170.60, 690.02) (162.81, 690.02)        /F1 0	<|special_separator|>
+(170.60, 677.65) (174.49, 677.65) (174.49, 690.02) (170.60, 690.02)        /F1 /	<|special_separator|>
+(174.49, 677.65) (182.27, 677.65) (182.27, 690.02) (174.49, 690.02)        /F1 6	<|special_separator|>
+(182.27, 677.65) (190.06, 677.65) (190.06, 690.02) (182.27, 690.02)        /F1 0	<|special_separator|>
+(190.06, 677.65) (195.66, 677.65) (195.66, 690.02) (190.06, 690.02)        /F1 °	<|special_separator|>
+(195.66, 677.65) (204.21, 677.65) (204.21, 690.02) (195.66, 690.02)        /F1 F
\ No newline at end of file
diff --git a/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.page_no_1.py.json.line.txt b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.page_no_1.py.json.line.txt
new file mode 100644
index 00000000..31153a83
--- /dev/null
+++ b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.page_no_1.py.json.line.txt
@@ -0,0 +1,2 @@
+(050.00, 697.65) (175.43, 697.65) (175.43, 710.02) (050.00, 710.02)        /F1 Temperature: 100°F	<|special_separator|>
+(050.00, 677.65) (204.21, 677.65) (204.21, 690.02) (050.00, 690.02)        /F1 Specific Gravity: 60/60°F
\ No newline at end of file
diff --git a/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.page_no_1.py.json.word.txt b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.page_no_1.py.json.word.txt
new file mode 100644
index 00000000..8ff005d7
--- /dev/null
+++ b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.page_no_1.py.json.word.txt
@@ -0,0 +1,5 @@
+(050.00, 697.65) (134.03, 697.65) (134.03, 710.02) (050.00, 710.02)        /F1 Temperature:	<|special_separator|>
+(137.92, 697.65) (175.43, 697.65) (175.43, 710.02) (137.92, 710.02)        /F1 100°F	<|special_separator|>
+(050.00, 677.65) (099.01, 677.65) (099.01, 690.02) (050.00, 690.02)        /F1 Specific	<|special_separator|>
+(102.91, 677.65) (151.14, 677.65) (151.14, 690.02) (102.91, 690.02)        /F1 Gravity:	<|special_separator|>
+(155.03, 677.65) (204.21, 677.65) (204.21, 690.02) (155.03, 690.02)        /F1 60/60°F
\ No newline at end of file
diff --git a/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.v1.json b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.v1.json
new file mode 100644
index 00000000..41d41c96
--- /dev/null
+++ b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.v1.json
@@ -0,0 +1,107 @@
+{
+  "info": {
+    "histograms": {
+      "mean-char-height": {
+        "/SUBSET+ArialMT": 0.6950222284786728
+      },
+      "mean-char-width": {
+        "/SUBSET+ArialMT": 6.214133230506241
+      },
+      "number-of-chars": {
+        "/SUBSET+ArialMT": 45
+      }
+    },
+    "styles": [
+      "/SUBSET+ArialMT"
+    ]
+  },
+  "pages": [
+    {
+      "cells": [
+        {
+          "angle": 0,
+          "box": {
+            "baseline": [
+              50,
+              700,
+              175.42599,
+              715.638
+            ],
+            "device": [
+              50,
+              697.03198,
+              175.42599,
+              712.66998
+            ]
+          },
+          "content": {
+            "rnormalized": "Temperature: 100\u00b0F"
+          },
+          "enumeration": {
+            "match": -1,
+            "type": -1
+          },
+          "font": {
+            "color": [
+              0,
+              0,
+              0,
+              255
+            ],
+            "name": "/SUBSET+ArialMT",
+            "size": 14
+          }
+        },
+        {
+          "angle": 0,
+          "box": {
+            "baseline": [
+              50,
+              680,
+              204.21001,
+              695.638
+            ],
+            "device": [
+              50,
+              677.03198,
+              204.21001,
+              692.66998
+            ]
+          },
+          "content": {
+            "rnormalized": "Specific Gravity: 60/60\u00b0F"
+          },
+          "enumeration": {
+            "match": -1,
+            "type": -1
+          },
+          "font": {
+            "color": [
+              0,
+              0,
+              0,
+              255
+            ],
+            "name": "/SUBSET+ArialMT",
+            "size": 14
+          }
+        }
+      ],
+      "dimensions": {
+        "bbox": [
+          0,
+          0,
+          612,
+          792
+        ],
+        "height": 792,
+        "width": 612
+      },
+      "height": 792,
+      "ignored-cells": [],
+      "images": [],
+      "paths": [],
+      "width": 612
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.v1.p=0.json b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.v1.p=0.json
new file mode 100644
index 00000000..41d41c96
--- /dev/null
+++ b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.v1.p=0.json
@@ -0,0 +1,107 @@
+{
+  "info": {
+    "histograms": {
+      "mean-char-height": {
+        "/SUBSET+ArialMT": 0.6950222284786728
+      },
+      "mean-char-width": {
+        "/SUBSET+ArialMT": 6.214133230506241
+      },
+      "number-of-chars": {
+        "/SUBSET+ArialMT": 45
+      }
+    },
+    "styles": [
+      "/SUBSET+ArialMT"
+    ]
+  },
+  "pages": [
+    {
+      "cells": [
+        {
+          "angle": 0,
+          "box": {
+            "baseline": [
+              50,
+              700,
+              175.42599,
+              715.638
+            ],
+            "device": [
+              50,
+              697.03198,
+              175.42599,
+              712.66998
+            ]
+          },
+          "content": {
+            "rnormalized": "Temperature: 100\u00b0F"
+          },
+          "enumeration": {
+            "match": -1,
+            "type": -1
+          },
+          "font": {
+            "color": [
+              0,
+              0,
+              0,
+              255
+            ],
+            "name": "/SUBSET+ArialMT",
+            "size": 14
+          }
+        },
+        {
+          "angle": 0,
+          "box": {
+            "baseline": [
+              50,
+              680,
+              204.21001,
+              695.638
+            ],
+            "device": [
+              50,
+              677.03198,
+              204.21001,
+              692.66998
+            ]
+          },
+          "content": {
+            "rnormalized": "Specific Gravity: 60/60\u00b0F"
+          },
+          "enumeration": {
+            "match": -1,
+            "type": -1
+          },
+          "font": {
+            "color": [
+              0,
+              0,
+              0,
+              255
+            ],
+            "name": "/SUBSET+ArialMT",
+            "size": 14
+          }
+        }
+      ],
+      "dimensions": {
+        "bbox": [
+          0,
+          0,
+          612,
+          792
+        ],
+        "height": 792,
+        "width": 612
+      },
+      "height": 792,
+      "ignored-cells": [],
+      "images": [],
+      "paths": [],
+      "width": 612
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.v2.json b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.v2.json
new file mode 100644
index 00000000..519dc48f
--- /dev/null
+++ b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.v2.json
@@ -0,0 +1,1219 @@
+{
+  "annotations": {
+    "form": null,
+    "language": null,
+    "meta_xml": null,
+    "table_of_contents": null
+  },
+  "info": {
+    "#-pages": 1,
+    "filename": "tests/data/regression/macroman_encoding_bug_demo.pdf"
+  },
+  "pages": [
+    {
+      "annotations": null,
+      "original": {
+        "cells": {
+          "data": [
+            [
+              50.0,
+              697.652,
+              58.554,
+              710.024,
+              50.0,
+              697.652,
+              58.554,
+              697.652,
+              58.554,
+              710.024,
+              50.0,
+              710.024,
+              "T",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              58.554,
+              697.652,
+              66.338,
+              710.024,
+              58.554,
+              697.652,
+              66.338,
+              697.652,
+              66.338,
+              710.024,
+              58.554,
+              710.024,
+              "e",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              66.338,
+              697.652,
+              78.0,
+              710.024,
+              66.338,
+              697.652,
+              78.0,
+              697.652,
+              78.0,
+              710.024,
+              66.338,
+              710.024,
+              "m",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              78.0,
+              697.652,
+              85.784,
+              710.024,
+              78.0,
+              697.652,
+              85.784,
+              697.652,
+              85.784,
+              710.024,
+              78.0,
+              710.024,
+              "p",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              85.784,
+              697.652,
+              93.568,
+              710.024,
+              85.784,
+              697.652,
+              93.568,
+              697.652,
+              93.568,
+              710.024,
+              85.784,
+              710.024,
+              "e",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              93.568,
+              697.652,
+              98.23,
+              710.024,
+              93.568,
+              697.652,
+              98.23,
+              697.652,
+              98.23,
+              710.024,
+              93.568,
+              710.024,
+              "r",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              98.23,
+              697.652,
+              106.014,
+              710.024,
+              98.23,
+              697.652,
+              106.014,
+              697.652,
+              106.014,
+              710.024,
+              98.23,
+              710.024,
+              "a",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              106.014,
+              697.652,
+              109.906,
+              710.024,
+              106.014,
+              697.652,
+              109.906,
+              697.652,
+              109.906,
+              710.024,
+              106.014,
+              710.024,
+              "t",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              109.906,
+              697.652,
+              117.69,
+              710.024,
+              109.906,
+              697.652,
+              117.69,
+              697.652,
+              117.69,
+              710.024,
+              109.906,
+              710.024,
+              "u",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              117.69,
+              697.652,
+              122.352,
+              710.024,
+              117.69,
+              697.652,
+              122.352,
+              697.652,
+              122.352,
+              710.024,
+              117.69,
+              710.024,
+              "r",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              122.352,
+              697.652,
+              130.136,
+              710.024,
+              122.352,
+              697.652,
+              130.136,
+              697.652,
+              130.136,
+              710.024,
+              122.352,
+              710.024,
+              "e",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              130.136,
+              697.652,
+              134.028,
+              710.024,
+              130.136,
+              697.652,
+              134.028,
+              697.652,
+              134.028,
+              710.024,
+              130.136,
+              710.024,
+              ":",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              134.028,
+              697.652,
+              137.92,
+              710.024,
+              134.028,
+              697.652,
+              137.92,
+              697.652,
+              137.92,
+              710.024,
+              134.028,
+              710.024,
+              " ",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              137.92,
+              697.652,
+              145.704,
+              710.024,
+              137.92,
+              697.652,
+              145.704,
+              697.652,
+              145.704,
+              710.024,
+              137.92,
+              710.024,
+              "1",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              145.704,
+              697.652,
+              153.488,
+              710.024,
+              145.704,
+              697.652,
+              153.488,
+              697.652,
+              153.488,
+              710.024,
+              145.704,
+              710.024,
+              "0",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              153.488,
+              697.652,
+              161.272,
+              710.024,
+              153.488,
+              697.652,
+              161.272,
+              697.652,
+              161.272,
+              710.024,
+              153.488,
+              710.024,
+              "0",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              161.272,
+              697.652,
+              166.872,
+              710.024,
+              161.272,
+              697.652,
+              166.872,
+              697.652,
+              166.872,
+              710.024,
+              161.272,
+              710.024,
+              "\u00b0",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              166.872,
+              697.652,
+              175.426,
+              710.024,
+              166.872,
+              697.652,
+              175.426,
+              697.652,
+              175.426,
+              710.024,
+              166.872,
+              710.024,
+              "F",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              50.0,
+              677.652,
+              59.338,
+              690.024,
+              50.0,
+              677.652,
+              59.338,
+              677.652,
+              59.338,
+              690.024,
+              50.0,
+              690.024,
+              "S",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              59.338,
+              677.652,
+              67.122,
+              690.024,
+              59.338,
+              677.652,
+              67.122,
+              677.652,
+              67.122,
+              690.024,
+              59.338,
+              690.024,
+              "p",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              67.122,
+              677.652,
+              74.906,
+              690.024,
+              67.122,
+              677.652,
+              74.906,
+              677.652,
+              74.906,
+              690.024,
+              67.122,
+              690.024,
+              "e",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              74.906,
+              677.652,
+              81.906,
+              690.024,
+              74.906,
+              677.652,
+              81.906,
+              677.652,
+              81.906,
+              690.024,
+              74.906,
+              690.024,
+              "c",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              81.906,
+              677.652,
+              85.014,
+              690.024,
+              81.906,
+              677.652,
+              85.014,
+              677.652,
+              85.014,
+              690.024,
+              81.906,
+              690.024,
+              "i",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              85.014,
+              677.652,
+              88.906,
+              690.024,
+              85.014,
+              677.652,
+              88.906,
+              677.652,
+              88.906,
+              690.024,
+              85.014,
+              690.024,
+              "f",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              88.906,
+              677.652,
+              92.014,
+              690.024,
+              88.906,
+              677.652,
+              92.014,
+              677.652,
+              92.014,
+              690.024,
+              88.906,
+              690.024,
+              "i",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              92.014,
+              677.652,
+              99.014,
+              690.024,
+              92.014,
+              677.652,
+              99.014,
+              677.652,
+              99.014,
+              690.024,
+              92.014,
+              690.024,
+              "c",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              99.014,
+              677.652,
+              102.906,
+              690.024,
+              99.014,
+              677.652,
+              102.906,
+              677.652,
+              102.906,
+              690.024,
+              99.014,
+              690.024,
+              " ",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              102.906,
+              677.652,
+              113.798,
+              690.024,
+              102.906,
+              677.652,
+              113.798,
+              677.652,
+              113.798,
+              690.024,
+              102.906,
+              690.024,
+              "G",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              113.798,
+              677.652,
+              118.46,
+              690.024,
+              113.798,
+              677.652,
+              118.46,
+              677.652,
+              118.46,
+              690.024,
+              113.798,
+              690.024,
+              "r",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              118.46,
+              677.652,
+              126.244,
+              690.024,
+              118.46,
+              677.652,
+              126.244,
+              677.652,
+              126.244,
+              690.024,
+              118.46,
+              690.024,
+              "a",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              126.244,
+              677.652,
+              133.244,
+              690.024,
+              126.244,
+              677.652,
+              133.244,
+              677.652,
+              133.244,
+              690.024,
+              126.244,
+              690.024,
+              "v",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              133.244,
+              677.652,
+              136.352,
+              690.024,
+              133.244,
+              677.652,
+              136.352,
+              677.652,
+              136.352,
+              690.024,
+              133.244,
+              690.024,
+              "i",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              136.352,
+              677.652,
+              140.244,
+              690.024,
+              136.352,
+              677.652,
+              140.244,
+              677.652,
+              140.244,
+              690.024,
+              136.352,
+              690.024,
+              "t",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              140.244,
+              677.652,
+              147.244,
+              690.024,
+              140.244,
+              677.652,
+              147.244,
+              677.652,
+              147.244,
+              690.024,
+              140.244,
+              690.024,
+              "y",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              147.244,
+              677.652,
+              151.136,
+              690.024,
+              147.244,
+              677.652,
+              151.136,
+              677.652,
+              151.136,
+              690.024,
+              147.244,
+              690.024,
+              ":",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              151.136,
+              677.652,
+              155.028,
+              690.024,
+              151.136,
+              677.652,
+              155.028,
+              677.652,
+              155.028,
+              690.024,
+              151.136,
+              690.024,
+              " ",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              155.028,
+              677.652,
+              162.812,
+              690.024,
+              155.028,
+              677.652,
+              162.812,
+              677.652,
+              162.812,
+              690.024,
+              155.028,
+              690.024,
+              "6",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              162.812,
+              677.652,
+              170.596,
+              690.024,
+              162.812,
+              677.652,
+              170.596,
+              677.652,
+              170.596,
+              690.024,
+              162.812,
+              690.024,
+              "0",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              170.596,
+              677.652,
+              174.488,
+              690.024,
+              170.596,
+              677.652,
+              174.488,
+              677.652,
+              174.488,
+              690.024,
+              170.596,
+              690.024,
+              "/",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              174.488,
+              677.652,
+              182.272,
+              690.024,
+              174.488,
+              677.652,
+              182.272,
+              677.652,
+              182.272,
+              690.024,
+              174.488,
+              690.024,
+              "6",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              182.272,
+              677.652,
+              190.056,
+              690.024,
+              182.272,
+              677.652,
+              190.056,
+              677.652,
+              190.056,
+              690.024,
+              182.272,
+              690.024,
+              "0",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              190.056,
+              677.652,
+              195.656,
+              690.024,
+              190.056,
+              677.652,
+              195.656,
+              677.652,
+              195.656,
+              690.024,
+              190.056,
+              690.024,
+              "\u00b0",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              195.656,
+              677.652,
+              204.21,
+              690.024,
+              195.656,
+              677.652,
+              204.21,
+              677.652,
+              204.21,
+              690.024,
+              195.656,
+              690.024,
+              "F",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ]
+          ],
+          "header": [
+            "x0",
+            "y0",
+            "x1",
+            "y1",
+            "r_x0",
+            "r_y0",
+            "r_x1",
+            "r_y1",
+            "r_x2",
+            "r_y2",
+            "r_x3",
+            "r_y3",
+            "text",
+            "rendering-mode",
+            "space-width",
+            "encoding-name",
+            "font-encoding",
+            "font-key",
+            "font-name",
+            "widget",
+            "left_to_right"
+          ]
+        },
+        "dimension": {
+          "angle": 0,
+          "bbox": [
+            0.0,
+            0.0,
+            612.0,
+            792.0
+          ],
+          "height": 792.0,
+          "page_boundary": "crop_box",
+          "rectangles": {
+            "art-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "bleed-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "crop-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "media-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "trim-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ]
+          },
+          "width": 612.0
+        },
+        "images": {
+          "data": [],
+          "header": [
+            "x0",
+            "y0",
+            "x1",
+            "y1"
+          ]
+        },
+        "lines": []
+      },
+      "page_number": 0,
+      "sanitized": {
+        "cells": {
+          "data": [
+            [
+              50.0,
+              697.652,
+              175.426,
+              710.024,
+              50.0,
+              697.652,
+              175.426,
+              697.652,
+              175.426,
+              710.024,
+              50.0,
+              710.024,
+              "Temperature: 100\u00b0F",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              50.0,
+              677.652,
+              204.21,
+              690.024,
+              50.0,
+              677.652,
+              204.21,
+              677.652,
+              204.21,
+              690.024,
+              50.0,
+              690.024,
+              "Specific Gravity: 60/60\u00b0F",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ]
+          ],
+          "header": [
+            "x0",
+            "y0",
+            "x1",
+            "y1",
+            "r_x0",
+            "r_y0",
+            "r_x1",
+            "r_y1",
+            "r_x2",
+            "r_y2",
+            "r_x3",
+            "r_y3",
+            "text",
+            "rendering-mode",
+            "space-width",
+            "encoding-name",
+            "font-encoding",
+            "font-key",
+            "font-name",
+            "widget",
+            "left_to_right"
+          ]
+        },
+        "dimension": {
+          "angle": 0,
+          "bbox": [
+            0.0,
+            0.0,
+            612.0,
+            792.0
+          ],
+          "height": 792.0,
+          "page_boundary": "crop_box",
+          "rectangles": {
+            "art-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "bleed-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "crop-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "media-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "trim-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ]
+          },
+          "width": 612.0
+        },
+        "images": {
+          "data": [],
+          "header": [
+            "x0",
+            "y0",
+            "x1",
+            "y1"
+          ]
+        },
+        "lines": []
+      }
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.v2.p=0.json b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.v2.p=0.json
new file mode 100644
index 00000000..b5c8a666
--- /dev/null
+++ b/tests/data/groundtruth/macroman_encoding_bug_demo.pdf.v2.p=0.json
@@ -0,0 +1,1434 @@
+{
+  "annotations": {
+    "form": null,
+    "language": null,
+    "meta_xml": null,
+    "table_of_contents": null
+  },
+  "info": {
+    "#-pages": 1,
+    "filename": "tests/data/regression/macroman_encoding_bug_demo.pdf"
+  },
+  "pages": [
+    {
+      "annotations": null,
+      "original": {
+        "cells": {
+          "data": [
+            [
+              50.0,
+              697.652,
+              58.554,
+              710.024,
+              50.0,
+              697.652,
+              58.554,
+              697.652,
+              58.554,
+              710.024,
+              50.0,
+              710.024,
+              "T",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              58.554,
+              697.652,
+              66.338,
+              710.024,
+              58.554,
+              697.652,
+              66.338,
+              697.652,
+              66.338,
+              710.024,
+              58.554,
+              710.024,
+              "e",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              66.338,
+              697.652,
+              78.0,
+              710.024,
+              66.338,
+              697.652,
+              78.0,
+              697.652,
+              78.0,
+              710.024,
+              66.338,
+              710.024,
+              "m",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              78.0,
+              697.652,
+              85.784,
+              710.024,
+              78.0,
+              697.652,
+              85.784,
+              697.652,
+              85.784,
+              710.024,
+              78.0,
+              710.024,
+              "p",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              85.784,
+              697.652,
+              93.568,
+              710.024,
+              85.784,
+              697.652,
+              93.568,
+              697.652,
+              93.568,
+              710.024,
+              85.784,
+              710.024,
+              "e",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              93.568,
+              697.652,
+              98.23,
+              710.024,
+              93.568,
+              697.652,
+              98.23,
+              697.652,
+              98.23,
+              710.024,
+              93.568,
+              710.024,
+              "r",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              98.23,
+              697.652,
+              106.014,
+              710.024,
+              98.23,
+              697.652,
+              106.014,
+              697.652,
+              106.014,
+              710.024,
+              98.23,
+              710.024,
+              "a",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              106.014,
+              697.652,
+              109.906,
+              710.024,
+              106.014,
+              697.652,
+              109.906,
+              697.652,
+              109.906,
+              710.024,
+              106.014,
+              710.024,
+              "t",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              109.906,
+              697.652,
+              117.69,
+              710.024,
+              109.906,
+              697.652,
+              117.69,
+              697.652,
+              117.69,
+              710.024,
+              109.906,
+              710.024,
+              "u",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              117.69,
+              697.652,
+              122.352,
+              710.024,
+              117.69,
+              697.652,
+              122.352,
+              697.652,
+              122.352,
+              710.024,
+              117.69,
+              710.024,
+              "r",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              122.352,
+              697.652,
+              130.136,
+              710.024,
+              122.352,
+              697.652,
+              130.136,
+              697.652,
+              130.136,
+              710.024,
+              122.352,
+              710.024,
+              "e",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              130.136,
+              697.652,
+              134.028,
+              710.024,
+              130.136,
+              697.652,
+              134.028,
+              697.652,
+              134.028,
+              710.024,
+              130.136,
+              710.024,
+              ":",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              134.028,
+              697.652,
+              137.92,
+              710.024,
+              134.028,
+              697.652,
+              137.92,
+              697.652,
+              137.92,
+              710.024,
+              134.028,
+              710.024,
+              " ",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              137.92,
+              697.652,
+              145.704,
+              710.024,
+              137.92,
+              697.652,
+              145.704,
+              697.652,
+              145.704,
+              710.024,
+              137.92,
+              710.024,
+              "1",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              145.704,
+              697.652,
+              153.488,
+              710.024,
+              145.704,
+              697.652,
+              153.488,
+              697.652,
+              153.488,
+              710.024,
+              145.704,
+              710.024,
+              "0",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              153.488,
+              697.652,
+              161.272,
+              710.024,
+              153.488,
+              697.652,
+              161.272,
+              697.652,
+              161.272,
+              710.024,
+              153.488,
+              710.024,
+              "0",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              161.272,
+              697.652,
+              166.872,
+              710.024,
+              161.272,
+              697.652,
+              166.872,
+              697.652,
+              166.872,
+              710.024,
+              161.272,
+              710.024,
+              "\u00b0",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              166.872,
+              697.652,
+              175.426,
+              710.024,
+              166.872,
+              697.652,
+              175.426,
+              697.652,
+              175.426,
+              710.024,
+              166.872,
+              710.024,
+              "F",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              50.0,
+              677.652,
+              59.338,
+              690.024,
+              50.0,
+              677.652,
+              59.338,
+              677.652,
+              59.338,
+              690.024,
+              50.0,
+              690.024,
+              "S",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              59.338,
+              677.652,
+              67.122,
+              690.024,
+              59.338,
+              677.652,
+              67.122,
+              677.652,
+              67.122,
+              690.024,
+              59.338,
+              690.024,
+              "p",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              67.122,
+              677.652,
+              74.906,
+              690.024,
+              67.122,
+              677.652,
+              74.906,
+              677.652,
+              74.906,
+              690.024,
+              67.122,
+              690.024,
+              "e",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              74.906,
+              677.652,
+              81.906,
+              690.024,
+              74.906,
+              677.652,
+              81.906,
+              677.652,
+              81.906,
+              690.024,
+              74.906,
+              690.024,
+              "c",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              81.906,
+              677.652,
+              85.014,
+              690.024,
+              81.906,
+              677.652,
+              85.014,
+              677.652,
+              85.014,
+              690.024,
+              81.906,
+              690.024,
+              "i",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              85.014,
+              677.652,
+              88.906,
+              690.024,
+              85.014,
+              677.652,
+              88.906,
+              677.652,
+              88.906,
+              690.024,
+              85.014,
+              690.024,
+              "f",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              88.906,
+              677.652,
+              92.014,
+              690.024,
+              88.906,
+              677.652,
+              92.014,
+              677.652,
+              92.014,
+              690.024,
+              88.906,
+              690.024,
+              "i",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              92.014,
+              677.652,
+              99.014,
+              690.024,
+              92.014,
+              677.652,
+              99.014,
+              677.652,
+              99.014,
+              690.024,
+              92.014,
+              690.024,
+              "c",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              99.014,
+              677.652,
+              102.906,
+              690.024,
+              99.014,
+              677.652,
+              102.906,
+              677.652,
+              102.906,
+              690.024,
+              99.014,
+              690.024,
+              " ",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              102.906,
+              677.652,
+              113.798,
+              690.024,
+              102.906,
+              677.652,
+              113.798,
+              677.652,
+              113.798,
+              690.024,
+              102.906,
+              690.024,
+              "G",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              113.798,
+              677.652,
+              118.46,
+              690.024,
+              113.798,
+              677.652,
+              118.46,
+              677.652,
+              118.46,
+              690.024,
+              113.798,
+              690.024,
+              "r",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              118.46,
+              677.652,
+              126.244,
+              690.024,
+              118.46,
+              677.652,
+              126.244,
+              677.652,
+              126.244,
+              690.024,
+              118.46,
+              690.024,
+              "a",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              126.244,
+              677.652,
+              133.244,
+              690.024,
+              126.244,
+              677.652,
+              133.244,
+              677.652,
+              133.244,
+              690.024,
+              126.244,
+              690.024,
+              "v",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              133.244,
+              677.652,
+              136.352,
+              690.024,
+              133.244,
+              677.652,
+              136.352,
+              677.652,
+              136.352,
+              690.024,
+              133.244,
+              690.024,
+              "i",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              136.352,
+              677.652,
+              140.244,
+              690.024,
+              136.352,
+              677.652,
+              140.244,
+              677.652,
+              140.244,
+              690.024,
+              136.352,
+              690.024,
+              "t",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              140.244,
+              677.652,
+              147.244,
+              690.024,
+              140.244,
+              677.652,
+              147.244,
+              677.652,
+              147.244,
+              690.024,
+              140.244,
+              690.024,
+              "y",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              147.244,
+              677.652,
+              151.136,
+              690.024,
+              147.244,
+              677.652,
+              151.136,
+              677.652,
+              151.136,
+              690.024,
+              147.244,
+              690.024,
+              ":",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              151.136,
+              677.652,
+              155.028,
+              690.024,
+              151.136,
+              677.652,
+              155.028,
+              677.652,
+              155.028,
+              690.024,
+              151.136,
+              690.024,
+              " ",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              155.028,
+              677.652,
+              162.812,
+              690.024,
+              155.028,
+              677.652,
+              162.812,
+              677.652,
+              162.812,
+              690.024,
+              155.028,
+              690.024,
+              "6",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              162.812,
+              677.652,
+              170.596,
+              690.024,
+              162.812,
+              677.652,
+              170.596,
+              677.652,
+              170.596,
+              690.024,
+              162.812,
+              690.024,
+              "0",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              170.596,
+              677.652,
+              174.488,
+              690.024,
+              170.596,
+              677.652,
+              174.488,
+              677.652,
+              174.488,
+              690.024,
+              170.596,
+              690.024,
+              "/",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              174.488,
+              677.652,
+              182.272,
+              690.024,
+              174.488,
+              677.652,
+              182.272,
+              677.652,
+              182.272,
+              690.024,
+              174.488,
+              690.024,
+              "6",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              182.272,
+              677.652,
+              190.056,
+              690.024,
+              182.272,
+              677.652,
+              190.056,
+              677.652,
+              190.056,
+              690.024,
+              182.272,
+              690.024,
+              "0",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              190.056,
+              677.652,
+              195.656,
+              690.024,
+              190.056,
+              677.652,
+              195.656,
+              677.652,
+              195.656,
+              690.024,
+              190.056,
+              690.024,
+              "\u00b0",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              195.656,
+              677.652,
+              204.21,
+              690.024,
+              195.656,
+              677.652,
+              204.21,
+              677.652,
+              204.21,
+              690.024,
+              195.656,
+              690.024,
+              "F",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ]
+          ],
+          "header": [
+            "x0",
+            "y0",
+            "x1",
+            "y1",
+            "r_x0",
+            "r_y0",
+            "r_x1",
+            "r_y1",
+            "r_x2",
+            "r_y2",
+            "r_x3",
+            "r_y3",
+            "text",
+            "rendering-mode",
+            "space-width",
+            "encoding-name",
+            "font-encoding",
+            "font-key",
+            "font-name",
+            "widget",
+            "left_to_right"
+          ]
+        },
+        "dimension": {
+          "angle": 0,
+          "bbox": [
+            0.0,
+            0.0,
+            612.0,
+            792.0
+          ],
+          "height": 792.0,
+          "page_boundary": "crop_box",
+          "rectangles": {
+            "art-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "bleed-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "crop-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "media-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "trim-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ]
+          },
+          "width": 612.0
+        },
+        "images": {
+          "data": [],
+          "header": [
+            "x0",
+            "y0",
+            "x1",
+            "y1"
+          ]
+        },
+        "line_cells": {
+          "data": [
+            [
+              50.0,
+              697.652,
+              175.426,
+              710.024,
+              50.0,
+              697.652,
+              175.426,
+              697.652,
+              175.426,
+              710.024,
+              50.0,
+              710.024,
+              "Temperature: 100\u00b0F",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              50.0,
+              677.652,
+              204.21,
+              690.024,
+              50.0,
+              677.652,
+              204.21,
+              677.652,
+              204.21,
+              690.024,
+              50.0,
+              690.024,
+              "Specific Gravity: 60/60\u00b0F",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ]
+          ],
+          "header": [
+            "x0",
+            "y0",
+            "x1",
+            "y1",
+            "r_x0",
+            "r_y0",
+            "r_x1",
+            "r_y1",
+            "r_x2",
+            "r_y2",
+            "r_x3",
+            "r_y3",
+            "text",
+            "rendering-mode",
+            "space-width",
+            "encoding-name",
+            "font-encoding",
+            "font-key",
+            "font-name",
+            "widget",
+            "left_to_right"
+          ]
+        },
+        "lines": [],
+        "word_cells": {
+          "data": [
+            [
+              50.0,
+              697.652,
+              134.028,
+              710.024,
+              50.0,
+              697.652,
+              134.028,
+              697.652,
+              134.028,
+              710.024,
+              50.0,
+              710.024,
+              "Temperature:",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              137.92,
+              697.652,
+              175.426,
+              710.024,
+              137.92,
+              697.652,
+              175.426,
+              697.652,
+              175.426,
+              710.024,
+              137.92,
+              710.024,
+              "100\u00b0F",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              50.0,
+              677.652,
+              99.014,
+              690.024,
+              50.0,
+              677.652,
+              99.014,
+              677.652,
+              99.014,
+              690.024,
+              50.0,
+              690.024,
+              "Specific",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              102.906,
+              677.652,
+              151.136,
+              690.024,
+              102.906,
+              677.652,
+              151.136,
+              677.652,
+              151.136,
+              690.024,
+              102.906,
+              690.024,
+              "Gravity:",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              155.028,
+              677.652,
+              204.21,
+              690.024,
+              155.028,
+              677.652,
+              204.21,
+              677.652,
+              204.21,
+              690.024,
+              155.028,
+              690.024,
+              "60/60\u00b0F",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ]
+          ],
+          "header": [
+            "x0",
+            "y0",
+            "x1",
+            "y1",
+            "r_x0",
+            "r_y0",
+            "r_x1",
+            "r_y1",
+            "r_x2",
+            "r_y2",
+            "r_x3",
+            "r_y3",
+            "text",
+            "rendering-mode",
+            "space-width",
+            "encoding-name",
+            "font-encoding",
+            "font-key",
+            "font-name",
+            "widget",
+            "left_to_right"
+          ]
+        }
+      },
+      "page_number": 0,
+      "sanitized": {
+        "cells": {
+          "data": [
+            [
+              50.0,
+              697.652,
+              175.426,
+              710.024,
+              50.0,
+              697.652,
+              175.426,
+              697.652,
+              175.426,
+              710.024,
+              50.0,
+              710.024,
+              "Temperature: 100\u00b0F",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ],
+            [
+              50.0,
+              677.652,
+              204.21,
+              690.024,
+              50.0,
+              677.652,
+              204.21,
+              677.652,
+              204.21,
+              690.024,
+              50.0,
+              690.024,
+              "Specific Gravity: 60/60\u00b0F",
+              -1,
+              3.892,
+              "/MacRomanEncoding",
+              "MACROMAN",
+              "/F1",
+              "/SUBSET+ArialMT",
+              false,
+              true
+            ]
+          ],
+          "header": [
+            "x0",
+            "y0",
+            "x1",
+            "y1",
+            "r_x0",
+            "r_y0",
+            "r_x1",
+            "r_y1",
+            "r_x2",
+            "r_y2",
+            "r_x3",
+            "r_y3",
+            "text",
+            "rendering-mode",
+            "space-width",
+            "encoding-name",
+            "font-encoding",
+            "font-key",
+            "font-name",
+            "widget",
+            "left_to_right"
+          ]
+        },
+        "dimension": {
+          "angle": 0,
+          "bbox": [
+            0.0,
+            0.0,
+            612.0,
+            792.0
+          ],
+          "height": 792.0,
+          "page_boundary": "crop_box",
+          "rectangles": {
+            "art-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "bleed-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "crop-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "media-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ],
+            "trim-bbox": [
+              0.0,
+              0.0,
+              612.0,
+              792.0
+            ]
+          },
+          "width": 612.0
+        },
+        "images": {
+          "data": [],
+          "header": [
+            "x0",
+            "y0",
+            "x1",
+            "y1"
+          ]
+        },
+        "lines": []
+      }
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/regression/macroman_encoding_bug_demo.pdf b/tests/data/regression/macroman_encoding_bug_demo.pdf
new file mode 100644
index 00000000..5796e7e8
Binary files /dev/null and b/tests/data/regression/macroman_encoding_bug_demo.pdf differ
diff --git a/tests/test_parse.py b/tests/test_parse.py
index bb5c04ab..ada91c19 100644
--- a/tests/test_parse.py
+++ b/tests/test_parse.py
@@ -215,7 +215,7 @@ def test_reference_documents_from_filenames():
     assert len(pdf_docs) > 0, "len(pdf_docs)==0 -> nothing to test"
 
     for pdf_doc_path in pdf_docs:
-        print(f"parsing {pdf_doc_path}")
+        # print(f"parsing {pdf_doc_path}")
 
         pdf_doc: PdfDocument = parser.load(
             path_or_stream=pdf_doc_path,
@@ -288,7 +288,7 @@ def test_reference_documents_from_filenames():
             img = pred_page.render_as_image(cell_unit=TextCellUnit.LINE)
             # img.show()
 
-            print(f"unloading page: {page_no}")
+            # print(f"unloading page: {page_no}")
             pdf_doc.unload_pages(page_range=(page_no, page_no + 1))
 
         toc: PdfTableOfContents = pdf_doc.get_table_of_contents()