use str.replace() instead of regex when not needed

spip2md/converter.py

@@ -161,106 +161,100 @@ spipToText = (
 isoToUtf = (
     # Broken encoding
     (  # Fix UTF-8 appostrophe that was interpreted as ISO 8859-1
-        compile("’"),
+        "’",
         r"’",
     ),
     (  # Fix UTF-8 † that was interpreted as ISO 8859-1
-        compile("‘"),
+        "‘",
         r"‘",
     ),
     (  # Fix UTF-8 é that was interpreted as ISO 8859-1
-        compile("eÌ\u0081"),
+        "eÌ\u0081",
         r"é",
     ),
     (  # Fix UTF-8 è that was interpreted as ISO 8859-1
-        compile("è"),
+        "è",
         r"è",
     ),
     (  # Fix UTF-8 ê that was interpreted as ISO 8859-1
-        compile("ê"),
+        "ê",
         r"ê",
     ),
     (  # Fix UTF-8 ê that was interpreted as ISO 8859-1
-        compile("ô"),
+        "ô",
         r"ô",
     ),
     (  # Fix UTF-8 î that was interpreted as ISO 8859-1
-        compile("î"),
+        "î",
         r"î",
     ),
     (  # Fix UTF-8 ï that was interpreted as ISO 8859-1
-        compile("ï"),
+        "ï",
         r"ï",
     ),
     (  # Fix UTF-8 ö that was interpreted as ISO 8859-1
-        compile("ö"),
+        "ö",
         r"ö",
     ),
     (  # Fix UTF-8 ö that was interpreted as ISO 8859-1
-        compile("ü"),
+        "ü",
         r"ü",
     ),
     (  # Fix UTF-8 é that was interpreted as ISO 8859-1
-        compile("à"),
+        "à",
         r"à",
     ),
     (  # Fix UTF-8 … that was interpreted as ISO 8859-1
-        compile("…"),
+        "…",
         r"…",
     ),
     (  # Fix UTF-8 “ that was interpreted as ISO 8859-1
-        compile("“"),
+        "“",
         r"“",
     ),
     (  # Fix UTF-8 ” that was interpreted as ISO 8859-1
-        compile("â€\u009d"),
+        "â€\u009d",
         r"”",
     ),
     (  # Fix UTF-8 – that was interpreted as ISO 8859-1
-        compile("–"),
+        "–",
         r"–",
     ),
     (  # Fix UTF-8 – that was interpreted as ISO 8859-1
-        compile("—"),
+        "—",
         r"—",
     ),
     (  # Fix UTF-8 − that was interpreted as ISO 8859-1
-        compile("â€\u0090"),
+        "â€\u0090",
         r"−",
     ),
     (  # Fix UTF-8 • that was interpreted as ISO 8859-1
-        compile("•"),
+        "•",
         r"•",
     ),
     (  # Fix UTF-8 ç that was interpreted as ISO 8859-1
-        compile("ç"),
+        "ç",
         r"ç",
     ),
     (  # Fix UTF-8 í that was interpreted as ISO 8859-1
-        compile("iÌ\u0081"),
+        "iÌ\u0081",
         r"í",
     ),
     # WARNING not sure
     (  # Fix UTF-8 é that was interpreted as ISO 8859-1
-        compile("eÌ "),
+        "eÌ ",
         r"é",
     ),
     (  # Fix UTF-8 † that was interpreted as ISO 8859-1
-        compile("†"),
+        "†",
         r"† ",
     ),
 )
 
 ## WARNING unknown broken encoding
 unknownIso = (
-    (  # unknown 
 + surroundings
-        compile(r"
"),
-        compile(r"
.*(?=\r?\n|$)"),
-    ),
-    (  # unknown â^† + surroundings
-        compile(r"∆"),
-        compile(r"∆.*(?=\r?\n|$)"),
-    ),
+    r"
",  # unknown 
 + surroundings
+    r"∆",  # unknown â^† + surroundings
 )
 
 
@@ -269,7 +263,7 @@ def convertBody(spipBody):
     for spip, markdown in spipToMarkdown:
         text = spip.sub(markdown, text)
     for iso, utf in isoToUtf:
-        text = iso.sub(utf, text)
+        text.replace(iso, utf)
     return text
 
 
@@ -278,5 +272,5 @@ def convertMeta(spipMeta):
     for spip, metadata in spipToText:
         text = spip.sub(metadata, text)
     for iso, utf in isoToUtf:
-        text = iso.sub(utf, text)
+        text.replace(iso, utf)
     return text

spip2md/iterator.py

@@ -1,4 +1,4 @@
-from re import escape
+from re import finditer
 
 from converter import convertBody, convertMeta, unknownIso
 from database import *
@@ -86,8 +86,8 @@ class Article:
     def getUnknownChars(self):
         errors: list = []
         for text in (self.title, self.text):
-            for _, surrounding in unknownIso:
-                for match in surrounding.finditer(text):
+            for char in unknownIso:
+                for match in finditer(char + r".*(?=\r?\n|$)", text):
                     errors.append(match.group())
         return errors
 
@@ -97,8 +97,8 @@ def highlightUnknownChars(text):
     COLOR = "\033[91m" + "\033[1m"  # Red + Bold
     RESET = "\033[0m"
     # Highlight in COLOR unknown chars in text
-    for char, _ in unknownIso:
-        for match in char.finditer(text):
+    for char in unknownIso:
+        for match in finditer(char, text):
             text = (
                 text[: match.start()]
                 + COLOR