From 1f6c9ac9d0d481c42a08cf05e1088e564d6bc00c Mon Sep 17 00:00:00 2001
From: Philip May <philip@may.la>
Date: Fri, 5 Jan 2024 14:27:48 +0100
Subject: [PATCH] Add XML tag detection function. (#139)

* Add XML tag detection function

* Add detection of XML tags in text.py

* Add clarification in has_xml_tag function

* Update copyright year in text.py
---
 mltb2/text.py      | 25 ++++++++++++++++++++++++-
 tests/test_text.py | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 60 insertions(+), 1 deletion(-)

diff --git a/mltb2/text.py b/mltb2/text.py
index d998c4e..8eae3d4 100644
--- a/mltb2/text.py
+++ b/mltb2/text.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2023 Philip May
+# Copyright (c) 2023-2024 Philip May
 # This software is distributed under the terms of the MIT license
 # which is available at https://opensource.org/licenses/MIT
 
@@ -54,6 +54,29 @@
 
 MULTI_SPACE_PATTERN: Pattern = re.compile(r" {2,}")
 
+XML_TAG_PATTERN: Pattern = re.compile(r"<\/?[\w:]+( \/|\/|)>")
+
+
+def has_xml_tag(text: str) -> bool:
+    """Check if text contains XML tags (one or multiple).
+
+    These are some XML tags we detect:
+
+    - ``<xml_tag>``
+    - ``<xml:tag>``
+    - ``</xml_tag>``
+    - ``<xml_tag/>``
+    - ``<xml_tag />``
+
+    While we do not detect ``a < b but x > y``.
+
+    Args:
+        text: The text to check.
+    Returns:
+        ``True`` if the text contains XML tags, ``False`` otherwise.
+    """
+    return re.search(XML_TAG_PATTERN, text) is not None
+
 
 def remove_invisible_characters(text: str) -> str:
     """Remove invisible characters from text.
diff --git a/tests/test_text.py b/tests/test_text.py
index 9c1d949..2d6551f 100644
--- a/tests/test_text.py
+++ b/tests/test_text.py
@@ -17,6 +17,7 @@
     clean_all_invisible_chars_and_whitespaces,
     has_invisible_characters,
     has_special_whitespaces,
+    has_xml_tag,
     remove_invisible_characters,
     replace_multiple_whitespaces,
     replace_special_whitespaces,
@@ -229,3 +230,38 @@ def test_normalize_counter_to_defaultdict_empty_counter():
 
     assert isinstance(normalized_counter, defaultdict)
     assert len(normalized_counter) == 0
+
+
+@pytest.mark.parametrize(
+    "text",
+    [
+        "Some text<ta_g>more text",
+        "Some text<ta:g>more text",
+        "Some text</tag>more text",
+        "Some text<tag/>more text",
+        "Some text<tag />more text",
+    ],
+)
+def test_has_xml_tag_with_tags(text: str):
+    assert has_xml_tag(text)
+
+
+@pytest.mark.parametrize(
+    "text",
+    [
+        "Some text",
+        "",
+        "a < b but x > y",
+    ],
+)
+def test_has_xml_tag_without_tags(text: str):
+    assert not has_xml_tag(text)
+
+
+@settings(max_examples=1000)
+@given(text())
+def test_has_xml_tag_hypothesis(text: str):
+    result = has_xml_tag(text)
+    if result:
+        assert "<" in text
+        assert ">" in text