From 37268b873ad65e6aff7b47485d20af8afa141099 Mon Sep 17 00:00:00 2001
From: Veronica Berglyd Olsen <1619840+vkbo@users.noreply.github.com>
Date: Fri, 25 Oct 2024 17:49:53 +0200
Subject: [PATCH] Add URL regex pattern

---
 novelwriter/constants.py              |  1 +
 novelwriter/text/patterns.py          |  6 ++++
 tests/test_text/test_text_patterns.py | 48 +++++++++++++++++++++++++--
 3 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/novelwriter/constants.py b/novelwriter/constants.py
index 3fa2d7c8..c7c3318a 100644
--- a/novelwriter/constants.py
+++ b/novelwriter/constants.py
@@ -60,6 +60,7 @@ class nwConst:
 
 class nwRegEx:
 
+    URL    = r"https?://(?:www\.|(?!www))[\w/()@:%_\+-.~#?&=]+"
     WORDS  = r"\b[^\s\-\+\/–—\[\]:]+\b"
     BREAK  = r"(?i)(?<!\\)(\[br\]\n?)"
     FMT_EI = r"(?<![\w\\])(_)(?![\s_])(.+?)(?<![\s\\])(\1)(?!\w)"
diff --git a/novelwriter/text/patterns.py b/novelwriter/text/patterns.py
index faf39679..539c0cf4 100644
--- a/novelwriter/text/patterns.py
+++ b/novelwriter/text/patterns.py
@@ -32,6 +32,7 @@ from novelwriter.constants import nwRegEx
 class RegExPatterns:
 
     # Static RegExes
+    _rxUrl     = re.compile(nwRegEx.URL, re.ASCII)
     _rxWords   = re.compile(nwRegEx.WORDS, re.UNICODE)
     _rxBreak   = re.compile(nwRegEx.BREAK, re.UNICODE)
     _rxItalic  = re.compile(nwRegEx.FMT_EI, re.UNICODE)
@@ -40,6 +41,11 @@ class RegExPatterns:
     _rxSCPlain = re.compile(nwRegEx.FMT_SC, re.UNICODE)
     _rxSCValue = re.compile(nwRegEx.FMT_SV, re.UNICODE)
 
+    @property
+    def url(self) -> re.Pattern:
+        """Find URLs."""
+        return self._rxUrl
+
     @property
     def wordSplit(self) -> re.Pattern:
         """Split text into words."""
diff --git a/tests/test_text/test_text_patterns.py b/tests/test_text/test_text_patterns.py
index 8877cc0c..455e1491 100644
--- a/tests/test_text/test_text_patterns.py
+++ b/tests/test_text/test_text_patterns.py
@@ -40,6 +40,48 @@ def allMatches(regEx: re.Pattern, text: str) -> list[list[str]]:
     return result
 
 
+@pytest.mark.core
+def testTextPatterns_Urls():
+    """Test the URL regex."""
+    regEx = REGEX_PATTERNS.url
+
+    valid = [
+        "http://example.com",
+        "http://example.com/",
+        "http://example.com/path+to+page",
+        "http://example.com/path-to-page",
+        "http://example.com/path_to_page",
+        "http://example.com/path~to~page",
+        "http://example.com/path/to/page",
+        "http://example.com/path/to/page.html",
+        "http://example.com/path/to/page.html#title",
+        "http://example.com/path/to/page.html#title%20here",
+        "http://example.com/path/to/page.html#title%20here",
+        "http://example.com/path/to/page?foo=bar&bar=baz",
+        "http://example.com/path/to/page.html?foo=bar&bar=baz",
+        "http://example.com/path/to/page.html#title?foo=bar&bar=baz",
+        "http://user:password@example.com/",
+        "http://www.example.com/",
+        "http://www.www.example.com/",
+        "http://www.www.www.example.com/",
+        "https://example.com",
+        "https://www.example.com/",
+    ]
+    invalid = [
+        "hppt://example.com/",
+        "sftp://example.com/",
+        "http:/example.com/",
+        "http://www example com/",
+        "http://www\texample\tcom/",
+    ]
+
+    for test in valid:
+        assert allMatches(regEx, f"Text {test} more text") == [[(test, 5, 5 + len(test))]]
+
+    for test in invalid:
+        assert allMatches(regEx, f"Text {test} more text") == []
+
+
 @pytest.mark.core
 def testTextPatterns_Words():
     """Test the word split regex."""
@@ -198,8 +240,10 @@ def testTextPatterns_ShortcodesPlain():
 
     assert allMatches(regEx, "one [x]two[/x] three") == []
 
-    # Line Break Substitution
-    # =======================
+
+@pytest.mark.core
+def testTextPatterns_LineBreakReplace():
+    """Test replacing forced line breaks."""
     regEx = REGEX_PATTERNS.lineBreak
 
     assert regEx.sub("\n", "one[br]two") == "one\ntwo"