From c3cb12e5e2021252dcf108e6d99b2720e0f79e69 Mon Sep 17 00:00:00 2001
From: Veronica Berglyd Olsen <1619840+vkbo@users.noreply.github.com>
Date: Sun, 22 Sep 2024 16:56:21 +0200
Subject: [PATCH] Use stdlib re for Markdown matching

---
 novelwriter/core/tokenizer.py         |  6 ++----
 novelwriter/gui/dochighlight.py       |  1 -
 novelwriter/text/patterns.py          | 20 ++++++++------------
 tests/test_text/test_text_patterns.py | 23 ++++++++++++++++-------
 4 files changed, 26 insertions(+), 24 deletions(-)

diff --git a/novelwriter/core/tokenizer.py b/novelwriter/core/tokenizer.py
index b977d962..7bcf594a 100644
--- a/novelwriter/core/tokenizer.py
+++ b/novelwriter/core/tokenizer.py
@@ -1109,11 +1109,9 @@ class Tokenizer(ABC):
 
         # Match Markdown
         for regEx, fmts in self._rxMarkdown:
-            rxItt = regEx.globalMatch(text, 0)
-            while rxItt.hasNext():
-                rxMatch = rxItt.next()
+            for match in re.finditer(regEx, text):
                 temp.extend(
-                    (rxMatch.capturedStart(n), rxMatch.capturedLength(n), fmt, "")
+                    (match.start(n), len(match.group(n)), fmt, "")
                     for n, fmt in enumerate(fmts) if fmt > 0
                 )
 
diff --git a/novelwriter/gui/dochighlight.py b/novelwriter/gui/dochighlight.py
index cb76e76b..5cf14e9a 100644
--- a/novelwriter/gui/dochighlight.py
+++ b/novelwriter/gui/dochighlight.py
@@ -41,7 +41,6 @@ from novelwriter.constants import nwHeaders, nwRegEx, nwUnicode
 from novelwriter.core.index import processComment
 from novelwriter.enum import nwComment
 from novelwriter.text.patterns import REGEX_PATTERNS
-from novelwriter.types import QRegExUnicode
 
 logger = logging.getLogger(__name__)
 
diff --git a/novelwriter/text/patterns.py b/novelwriter/text/patterns.py
index 4d60222e..06c76b2a 100644
--- a/novelwriter/text/patterns.py
+++ b/novelwriter/text/patterns.py
@@ -23,6 +23,8 @@ along with this program. If not, see <https://www.gnu.org/licenses/>.
 """
 from __future__ import annotations
 
+import re
+
 from PyQt5.QtCore import QRegularExpression
 
 from novelwriter import CONFIG
@@ -33,25 +35,19 @@ from novelwriter.types import QRegExUnicode
 class RegExPatterns:
 
     @property
-    def markdownItalic(self) -> QRegularExpression:
+    def markdownItalic(self) -> re.Pattern:
         """Markdown italic style."""
-        rxRule = QRegularExpression(nwRegEx.FMT_EI)
-        rxRule.setPatternOptions(QRegExUnicode)
-        return rxRule
+        return re.compile(nwRegEx.FMT_EI, re.UNICODE)
 
     @property
-    def markdownBold(self) -> QRegularExpression:
+    def markdownBold(self) -> re.Pattern:
         """Markdown bold style."""
-        rxRule = QRegularExpression(nwRegEx.FMT_EB)
-        rxRule.setPatternOptions(QRegExUnicode)
-        return rxRule
+        return re.compile(nwRegEx.FMT_EB, re.UNICODE)
 
     @property
-    def markdownStrike(self) -> QRegularExpression:
+    def markdownStrike(self) -> re.Pattern:
         """Markdown strikethrough style."""
-        rxRule = QRegularExpression(nwRegEx.FMT_ST)
-        rxRule.setPatternOptions(QRegExUnicode)
-        return rxRule
+        return re.compile(nwRegEx.FMT_ST, re.UNICODE)
 
     @property
     def shortcodePlain(self) -> QRegularExpression:
diff --git a/tests/test_text/test_text_patterns.py b/tests/test_text/test_text_patterns.py
index 1b4623fd..b421db52 100644
--- a/tests/test_text/test_text_patterns.py
+++ b/tests/test_text/test_text_patterns.py
@@ -20,6 +20,8 @@ along with this program. If not, see <https://www.gnu.org/licenses/>.
 """
 from __future__ import annotations
 
+import re
+
 import pytest
 
 from PyQt5.QtCore import QRegularExpression
@@ -32,13 +34,20 @@ from novelwriter.text.patterns import REGEX_PATTERNS
 def allMatches(regEx: QRegularExpression, text: str) -> list[list[str]]:
     """Get all matches for a regex."""
     result = []
-    itt = regEx.globalMatch(text, 0)
-    while itt.hasNext():
-        match = itt.next()
-        result.append([
-            (match.captured(n), match.capturedStart(n), match.capturedEnd(n))
-            for n in range(match.lastCapturedIndex() + 1)
-        ])
+    if isinstance(regEx, QRegularExpression):
+        itt = regEx.globalMatch(text, 0)
+        while itt.hasNext():
+            match = itt.next()
+            result.append([
+                (match.captured(n), match.capturedStart(n), match.capturedEnd(n))
+                for n in range(match.lastCapturedIndex() + 1)
+            ])
+    else:
+        for match in re.finditer(regEx, text):
+            result.append([
+                (match.group(n), match.start(n), match.end(n))
+                for n in range((match.lastindex or -1) + 1)
+            ])
     return result