rename highlight-patterns()

Author: ashariyar

pdfalyzer/output/theme.py

@@ -22,7 +22,7 @@
 from pdfalyzer.util import adobe_strings
 from pdfalyzer.util.helpers.collections_helper import prefix_keys, safe_json
 from pdfalyzer.util.helpers.rich_helper import vertically_padded_panel
-from pdfalyzer.util.helpers.string_helper import regex_to_highlight_pattern
+from pdfalyzer.util.helpers.string_helper import highlight_pattern
 
 ClassStyle = namedtuple('ClassStyle', ['cls', 'style'])
 
@@ -73,6 +73,8 @@
     ClassStyle(NoneType, NULL_STYLE),
 ]
 
+PDF_OBJ_TYPE_STYLE_DICT = {f"{cs.cls.__name__}": cs.style for cs in PDF_OBJ_TYPE_STYLES}
+
 # Subclasses of the key type will be styled with the value string
 OBJ_TYPE_STYLES = PDF_OBJ_TYPE_STYLES + [
     ClassStyle(Number, 'cyan bold'),
@@ -146,28 +148,22 @@
     adobe_strings.TRUE:                                        'green bold',
 })
 
+# Compile regexes as keys
+NODE_STYLE_REGEXES = {re.compile(k): v for k, v in NODE_STYLES_BASE_DICT.items()}
+
+# Unite class styles for things like ArrayObject with node styles for things like /Parent
 NODE_STYLES_THEME_DICT = {
     **PdfHighlighter.prefix_styles({k.removeprefix('/'): v for k, v in NODE_STYLES_BASE_DICT.items()}),
-    **PdfHighlighter.prefix_styles({f"{cs.cls.__name__}": cs.style for cs in PDF_OBJ_TYPE_STYLES})
+    **PdfHighlighter.prefix_styles(PDF_OBJ_TYPE_STYLE_DICT)
 }
 
+# Merge all the theme dicts
 LOG_THEME_DICT = LogHighlighter.prefix_styles(LOG_HIGHLIGHT_STYLES)
 COMPLETE_THEME_DICT = {**PDFALYZER_THEME_DICT, **LOG_THEME_DICT, **NODE_STYLES_THEME_DICT}
 
-# Compile regexes as keys
-NODE_STYLE_REGEXES = {re.compile(k): v for k, v in NODE_STYLES_BASE_DICT.items()}
-
-
 # Add patterns to highlighters
-LogHighlighter.set_highlights(
-    LOG_HIGHLIGHT_PATTERNS +
-    [regex_to_highlight_pattern(cs.cls.__name__) for cs in PDF_OBJ_TYPE_STYLES]
-)
-
-PdfHighlighter.set_highlights(
-    [regex_to_highlight_pattern(r) for r in NODE_STYLE_REGEXES.keys()]
-)
-
+LogHighlighter.set_highlights(LOG_HIGHLIGHT_PATTERNS + [highlight_pattern(k) for k in PDF_OBJ_TYPE_STYLE_DICT.keys()])
+PdfHighlighter.set_highlights([highlight_pattern(r) for r in NODE_STYLE_REGEXES.keys()])
 
 # Push themes into the console objects that manage stdout.
 console.push_theme(Theme(COMPLETE_THEME_DICT))

pdfalyzer/util/helpers/string_helper.py

@@ -70,6 +70,22 @@ def has_a_common_substring(strings: list[str]) -> bool:
     return all([is_substring_of_longer_strings_in_list(s, strings) for s in strings])
 
 
+def highlight_pattern(regex: re.Pattern | str) -> str:
+    """Build a rich.Highlighter style pattern, e.g. `(?P<stream_object>((De|En)coded)?StreamObject)`."""
+    pattern = regex.pattern if isinstance(regex, re.Pattern) else regex
+    label = regex_to_capture_group_label(regex)
+
+    if len(pattern) <= 2:
+        pattern = fr"^{pattern}$"
+    else:
+        pattern = fr"{pattern}\b".removeprefix('/')
+
+        if not pattern.startswith('^'):
+            pattern = fr"[\b/]{pattern}"
+
+    return fr"(?P<{label}>{pattern})"
+
+
 def is_array_idx(address: str) -> bool:
     """True if address looks like '[23]'."""
     return bool(ARRAY_IDX_REGEX.match(address))
@@ -118,22 +134,6 @@ def regex_to_capture_group_label(pattern: re.Pattern | str) -> str:
     return NON_WORD_CHAR_REGEX.sub('', pattern.replace('|', '_'))
 
 
-def regex_to_highlight_pattern(regex: re.Pattern | str) -> str:
-    """(?P<stream_object>((De|En)coded)?StreamObject)."""
-    pattern = regex.pattern if isinstance(regex, re.Pattern) else regex
-    label = regex_to_capture_group_label(regex)
-
-    if len(pattern) <= 2:
-        pattern = fr"^{pattern}$"
-    else:
-        pattern = fr"{pattern}\b".removeprefix('/')
-
-        if not pattern.startswith('^'):
-            pattern = fr"[\b/]{pattern}"
-
-    return fr"(?P<{label}>{pattern})"
-
-
 def replace_digits(string_with_digits: str) -> str:
     """Turn all digits to X chars in a string."""
     return DIGIT_REGEX.sub('x', string_with_digits)

tests/pdfalyzer/helpers/test_string_helper.py

@@ -36,6 +36,6 @@ def test_regex_to_capture_group_label():
 
 
 def test_regex_to_highlight_pattern():
-    assert regex_to_highlight_pattern(OBJ_REGEX) == r"(?P<JavaScript_JS_OpenAction>^(JavaScript|JS|OpenAction)\b)"
-    assert regex_to_highlight_pattern(OBJ_REGEX.pattern[1:]) == r"(?P<JavaScript_JS_OpenAction>[\b/](JavaScript|JS|OpenAction)\b)"
-    assert regex_to_highlight_pattern(re.compile('/W')) == r"(?P<W>^/W$)"
+    assert highlight_pattern(OBJ_REGEX) == r"(?P<JavaScript_JS_OpenAction>^(JavaScript|JS|OpenAction)\b)"
+    assert highlight_pattern(OBJ_REGEX.pattern[1:]) == r"(?P<JavaScript_JS_OpenAction>[\b/](JavaScript|JS|OpenAction)\b)"
+    assert highlight_pattern(re.compile('/W')) == r"(?P<W>^/W$)"