Selectable naming schemes

standardize_test_format/__init__.py

@@ -7,6 +7,16 @@ Is capable of migrating from Javadoc based property specification to the
 """
 
 import re
+import enum
+import hashlib
+
+class NamingScheme(enum.Enum):
+    PRESERVE = 'preserve'
+    HASH_OF_DESC  = 'hash'
+    FROM_DESC = 'desc'
+
+
+
 
 PATTERN_JAVADOC = r'/\*\*(?P<javadoc>.*(\n\s*\*.*)*?)\s*\*/'
 PATTERN_DISPLAY_NAME_EXPRESSION = r'\s*(?:"[^"]*?")(?:\s*\+\s*"[^"]*?")*\s*'
@@ -33,6 +43,7 @@ IGNORABLE_WORDS_IN_NAME = frozenset(
     {
         '',
         'a',
+        'an',
         'the',
         'is',
         'are',
@@ -68,9 +79,6 @@ def format_test_prefix(
 
 
 def to_camel_case_word(word: str, first: bool = False) -> str | None:
-    word = word.strip()
-    if word.lower() in IGNORABLE_WORDS_IN_NAME:
-        return None
     if len(word) > 1 and word.upper() == word:
         word = word.lower()
     return (word[0].lower() if first else word[0].upper()) + word[1:]
@@ -82,16 +90,21 @@ def to_camel_case(description: str) -> str:
         .replace('.', ' ')
         .replace('"', ' ')
         .replace('+', ' ')
+        .replace('-', ' ')
+        .replace(':', ' ')
+        .replace('\'', '')
         .strip(' \t.')
     )
     words = description.split(' ')
 
+    words = [w.strip() for w in words]
+    words = [w for w in words if w.lower() not in IGNORABLE_WORDS_IN_NAME]
+
     words[0] = to_camel_case_word(words[0], first=True)
     for i in range(1, len(words)):
         words[i] = to_camel_case_word(words[i])
 
     words = [w for w in words if w]
-
     return ''.join(words)
 
 
@@ -105,7 +118,10 @@ def parse_javadoc_to_description(text: str | None):
     if text is None:
         return ''
     text = re.sub(r'\n\s*\*', ' ', text).strip()
+    text = re.sub(r'\{@link\s+(\w+)#(\w+)\}', r'\1 \2', text)
     text = re.sub(r'\{@link\s+(\w+)\}', r'\1', text)
+    text = re.sub(r'<p>', r'', text)
+    text = re.sub(r'</?b>', r'', text)
     return text
 
 
@@ -120,8 +136,10 @@ def parse_display_name_to_description(text: str | None):
     return text
 
 
+
 def replace_test_pattern(
     match: re.Match, with_javadoc: bool, with_display_name: bool,
+    naming_scheme: NamingScheme,
 ) -> str:
     javadoc = parse_javadoc_to_description(match.group('javadoc'))
 
@@ -131,9 +149,20 @@ def replace_test_pattern(
     display = parse_display_name_to_description(match.group('display'))
 
     description = display or javadoc or from_camel_case(name)
+    description = re.sub(r'[ \t]+', ' ', description)
+
+    if naming_scheme == NamingScheme.PRESERVE:
+        pass
+    elif naming_scheme == NamingScheme.FROM_DESC:
+        name = to_camel_case(description)
+    elif naming_scheme == NamingScheme.HASH_OF_DESC:
+        h = hashlib.sha256()
+        h.update(description.encode('utf8'))
+        name = 'test'+h.hexdigest()
+        del h
 
     return format_test_prefix(
-        to_camel_case(description),
+        name,
         description,
         annotation,
         visibility,
@@ -145,9 +174,9 @@ def replace_test_pattern(
 IMPORT_DISPLAY_NAME = 'import org.junit.jupiter.api.DisplayName;'
 
 
-def standardize_java_text(text: str, with_javadoc: bool, with_display_name: bool):
+def standardize_java_text(text: str, with_javadoc: bool, with_display_name: bool, naming_scheme: NamingScheme):
     text = TEST_PATTERN.sub(
-        lambda m: replace_test_pattern(m, with_javadoc, with_display_name), text,
+        lambda m: replace_test_pattern(m, with_javadoc, with_display_name, naming_scheme), text,
     )
     if '@DisplayName' in text and IMPORT_DISPLAY_NAME not in text:
         lines = text.split('\n')

standardize_test_format/__main__.py

@@ -1,7 +1,7 @@
 import argparse
 import pathlib
 
-from . import standardize_java_text
+from . import standardize_java_text, NamingScheme
 
 
 def test_files(repo: pathlib.Path) -> list[pathlib.Path]:
@@ -9,12 +9,13 @@ def test_files(repo: pathlib.Path) -> list[pathlib.Path]:
 
 
 def standardize_in_file(
-    path: pathlib.Path, inline: bool, with_javadoc: bool, with_display_name: bool,
+    path: pathlib.Path, inline: bool, with_javadoc: bool, with_display_name:
+    bool, naming_scheme: NamingScheme,
 ):
     with open(path) as f:
         text = f.read()
 
-    text_updated = standardize_java_text(text, with_javadoc, with_display_name)
+    text_updated = standardize_java_text(text, with_javadoc, with_display_name, naming_scheme=naming_scheme)
     if text_updated == text:
         return
 
@@ -31,6 +32,7 @@ def argument_parser():
     argparser.add_argument('-i', action='store_true')
     argparser.add_argument('--javadoc', action='store_true')
     argparser.add_argument('--displayname', action='store_true')
+    argparser.add_argument('--naming', type=NamingScheme, choices=list(NamingScheme), default=NamingScheme.FROM_DESC)
     return argparser
 
 
@@ -43,6 +45,7 @@ def main():
             inline=args.i,
             with_javadoc=args.javadoc,
             with_display_name=args.displayname,
+            naming_scheme=args.naming,
         )