Merge pull request #3347 from PyWoody/highlight_regex_compiled

highlight_regex in rich.text.Text Now Expects a Compiled Regular Expression (re.compile) Has Been Passed

CHANGELOG.md

@@ -55,6 +55,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Running tests in environment with `FORCE_COLOR` or `NO_COLOR` environment variables
 - ansi decoder will now strip problematic private escape sequences (like `\x1b7`) https://github.com/Textualize/rich/pull/3278/
 - Tree's ASCII_GUIDES and TREE_GUIDES constants promoted to class attributes
+- `rich.Text.highlight_regex` now accepts a regular expression object https://github.com/Textualize/rich/pull/3347
 
 ### Added
 

CONTRIBUTORS.md

@@ -87,6 +87,7 @@ The following people have contributed to the development of Rich:
 - [Pierro](https://github.com/xpierroz)
 - [Bernhard Wagner](https://github.com/bwagner)
 - [Aaron Beaudoin](https://github.com/AaronBeaudoin)
+- [Sam Woodward](https://github.com/PyWoody)
 - [L. Yeung](https://github.com/lewis-yeung)
 - [chthollyphile](https://github.com/chthollyphile)
 - [Jonathan Helmus](https://github.com/jjhelmus)

rich/text.py

@@ -591,7 +591,7 @@ class Text(JupyterMixin):
 
     def highlight_regex(
         self,
-        re_highlight: str,
+        re_highlight: Union[re.Pattern, str],
         style: Optional[Union[GetStyleCallable, StyleType]] = None,
         *,
         style_prefix: str = "",
@@ -600,7 +600,7 @@ class Text(JupyterMixin):
         translated to styles.
 
         Args:
-            re_highlight (str): A regular expression.
+            re_highlight (Union[re.Pattern, str]): A regular expression object or string.
             style (Union[GetStyleCallable, StyleType]): Optional style to apply to whole match, or a callable
                 which accepts the matched text and returns a style. Defaults to None.
             style_prefix (str, optional): Optional prefix to add to style group names.
@@ -612,7 +612,9 @@ class Text(JupyterMixin):
         append_span = self._spans.append
         _Span = Span
         plain = self.plain
-        for match in re.finditer(re_highlight, plain):
+        if isinstance(re_highlight, str):
+            re_highlight = re.compile(re_highlight)
+        for match in re_highlight.finditer(plain):
             get_span = match.span
             if style:
                 start, end = get_span()

tests/test_text.py

@@ -1,3 +1,4 @@
+import re
 from io import StringIO
 from typing import List
 
@@ -159,6 +160,7 @@ def test_stylize_negative_index():
 
 
 def test_highlight_regex():
+    # As a string
     text = Text("peek-a-boo")
 
     count = text.highlight_regex(r"NEVER_MATCH", "red")
@@ -176,6 +178,7 @@ def test_highlight_regex():
     ]
 
     text = Text("Ada Lovelace, Alan Turing")
+
     count = text.highlight_regex(
         r"(?P<yellow>[A-Za-z]+)[ ]+(?P<red>[A-Za-z]+)(?P<NEVER_MATCH>NEVER_MATCH)*"
     )
@@ -189,16 +192,52 @@ def test_highlight_regex():
         Span(19, 25, "red"),  # Turing
     ]
 
+    # As a regular expression object
+    text = Text("peek-a-boo")
+
+    count = text.highlight_regex(re.compile(r"NEVER_MATCH"), "red")
+    assert count == 0
+    assert len(text._spans) == 0
+
+    # text: peek-a-boo
+    # indx: 0123456789
+    count = text.highlight_regex(re.compile(r"[a|e|o]+"), "red")
+    assert count == 3
+    assert sorted(text._spans) == [
+        Span(1, 3, "red"),
+        Span(5, 6, "red"),
+        Span(8, 10, "red"),
+    ]
+
+    text = Text("Ada Lovelace, Alan Turing")
+
+    count = text.highlight_regex(
+        re.compile(
+            r"(?P<yellow>[A-Za-z]+)[ ]+(?P<red>[A-Za-z]+)(?P<NEVER_MATCH>NEVER_MATCH)*"
+        )
+    )
+
+    # The number of matched name should be 2
+    assert count == 2
+    assert sorted(text._spans) == [
+        Span(0, 3, "yellow"),  # Ada
+        Span(4, 12, "red"),  # Lovelace
+        Span(14, 18, "yellow"),  # Alan
+        Span(19, 25, "red"),  # Turing
+    ]
+
 
 def test_highlight_regex_callable():
     text = Text("Vulnerability CVE-2018-6543 detected")
     re_cve = r"CVE-\d{4}-\d+"
+    compiled_re_cve = re.compile(r"CVE-\d{4}-\d+")
 
     def get_style(text: str) -> Style:
         return Style.parse(
             f"bold yellow link https://cve.mitre.org/cgi-bin/cvekey.cgi?keyword={text}"
         )
 
+    # string
     count = text.highlight_regex(re_cve, get_style)
     assert count == 1
     assert len(text._spans) == 1
@@ -209,6 +248,20 @@ def test_highlight_regex_callable():
         == "https://cve.mitre.org/cgi-bin/cvekey.cgi?keyword=CVE-2018-6543"
     )
 
+    # Clear the tracked _spans for the regular expression object's use
+    text._spans.clear()
+
+    # regular expression object
+    count = text.highlight_regex(compiled_re_cve, get_style)
+    assert count == 1
+    assert len(text._spans) == 1
+    assert text._spans[0].start == 14
+    assert text._spans[0].end == 27
+    assert (
+        text._spans[0].style.link
+        == "https://cve.mitre.org/cgi-bin/cvekey.cgi?keyword=CVE-2018-6543"
+    )
+
 
 def test_highlight_words():
     text = Text("Do NOT! touch anything!")