fix: resolve CI/CD test and linting issues

.gitea/workflows/ci.yml

@@ -26,7 +26,7 @@ jobs:
         run: pytest tests/ -v
 
       - name: Run linter
-        run: ruff check .
+        run: ruff check regex_humanizer/ tests/
 
       - name: Run type check
         run: mypy regex_humanizer/

.github/workflows/ci.yml

@@ -0,0 +1,49 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.9', '3.10', '3.11', '3.12']
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e ".[dev]"
+
+      - name: Run tests
+        run: pytest tests/ -v --cov=regex_humanizer
+
+      - name: Run linting
+        run: ruff check regex_humanizer/ tests/
+
+  i18n-check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install i18n-key-sync
+        run: pip install -e .
+
+      - name: Validate i18n keys
+        run: i18n-key-sync validate ./i18n_key_sync --strict

pyproject.toml

@@ -30,8 +30,8 @@ dependencies = [
 dev = [
     "pytest>=7.0",
     "pytest-cov",
-    "flake8",
-    "mypy",
+    "ruff>=0.1.0",
+    "mypy>=1.0.0",
     "black",
     "isort",
 ]
@@ -57,7 +57,7 @@ profile = "black"
 line_length = 100
 
 [tool.mypy]
-python_version = "3.8"
+python_version = "3.9"
 warn_return_any = true
 warn_unused_configs = true
 ignore_missing_imports = true

regex_humanizer/cli.py

@@ -1,10 +1,11 @@
 """Main CLI module for Regex Humanizer."""
 
 import json as json_module
+from typing import List
 
 import click
 
-from .parser import parse_regex, ParseError
+from .parser import ASTNode, ParseError
 from .converter import convert_to_english, convert_to_english_verbose
 from .examples import generate_examples
 from .flavors import (
@@ -72,7 +73,7 @@ def explain(pattern: str, flavor: str, verbose: bool, output_format: str):
                 click.echo(f"Flavor: {result['flavor']}")
                 click.echo(f"\nDescription:\n{result['description']}")
                 if result.get('structure'):
-                    click.echo(f"\nStructure:")
+                    click.echo("\nStructure:")
                     for item in result['structure']:
                         click.echo(f"  - {item}")
         else:
@@ -87,7 +88,7 @@ def explain(pattern: str, flavor: str, verbose: bool, output_format: str):
 
         warnings = get_compatibility_warnings(pattern, flavor)
         if warnings:
-            click.echo(f"\nCompatibility warnings:")
+            click.echo("\nCompatibility warnings:")
             for w in warnings:
                 click.echo(f"  [{w.severity.upper()}] {w.feature}: {w.message}")
 
@@ -150,7 +151,7 @@ def generate(pattern: str, flavor: str, count: int, output_format: str):
         else:
             click.echo(f"\nPattern: {pattern}")
             click.echo(f"Flavor: {flavor}")
-            click.echo(f"\nMatching examples:")
+            click.echo("\nMatching examples:")
             for i, example in enumerate(examples, 1):
                 click.echo(f"  {i}. {example}")
 
@@ -198,7 +199,7 @@ def from_english(description: str, flavor: str, output_format: str):
             click.echo(f"Flavor: {result['flavor']}")
 
             if result.get('warnings'):
-                click.echo(f"\nWarnings:")
+                click.echo("\nWarnings:")
                 for w in result['warnings']:
                     click.echo(f"  - {w}")
 
@@ -226,7 +227,7 @@ def build(flavor: str):
     click.echo(f"Flavor: {flavor}")
     click.echo("Enter 'quit' to exit, 'back' to go back, 'done' when finished.\n")
 
-    pattern_parts = []
+    pattern_parts: List[ASTNode] = []
 
     while True:
         current_pattern = "".join(p.to_regex() if hasattr(p, 'to_regex') else str(p) for p in pattern_parts)

regex_humanizer/converter/converter.py

@@ -1,4 +1,6 @@
-from typing import List, Optional
+"""Implementation of regex to English conversion."""
+
+from typing import Any, List
 
 from ..parser import (
     Alternation,
@@ -15,6 +17,7 @@ from ..parser import (
 
 
 def quantifier_description(quantifier: Quantifier, child_desc: str) -> str:
+    """Generate description for a quantifier."""
     if quantifier.min == 0 and quantifier.max == 1:
         base = "optionally"
     elif quantifier.min == 0 and quantifier.max == Quantifier.MAX_UNBOUNDED:
@@ -37,6 +40,7 @@ def quantifier_description(quantifier: Quantifier, child_desc: str) -> str:
 
 
 def literal_description(node: Literal) -> str:
+    """Generate description for a literal character."""
     if node.value == " ":
         return "a space"
     elif node.value == "\t":
@@ -52,6 +56,7 @@ def literal_description(node: Literal) -> str:
 
 
 def character_class_description(node: CharacterClass) -> str:
+    """Generate description for a character class."""
     parts = []
 
     if node.inverted:
@@ -90,6 +95,7 @@ def character_class_description(node: CharacterClass) -> str:
 
 
 def special_sequence_description(node: SpecialSequence) -> str:
+    """Generate description for a special sequence."""
     sequences = {
         ".": "any single character",
         r"\d": "a digit (0-9)",
@@ -111,6 +117,7 @@ def special_sequence_description(node: SpecialSequence) -> str:
 
 
 def anchor_description(node: Anchor) -> str:
+    """Generate description for an anchor."""
     anchors = {
         "^": "the start of the string",
         "$": "the end of the string",
@@ -121,6 +128,7 @@ def anchor_description(node: Anchor) -> str:
 
 
 def group_description(node: Group) -> str:
+    """Generate description for a group."""
     if node.name:
         name_desc = f"named '{node.name}'"
     elif not node.capturing:
@@ -136,6 +144,7 @@ def group_description(node: Group) -> str:
 
 
 def alternation_description(node: Alternation) -> str:
+    """Generate description for an alternation."""
     option_descs = []
     for option in node.options:
         if option:
@@ -150,6 +159,7 @@ def alternation_description(node: Alternation) -> str:
 
 
 def backreference_description(node: Backreference) -> str:
+    """Generate description for a backreference."""
     if isinstance(node.reference, int):
         return f"whatever was matched by capture group {node.reference}"
     else:
@@ -157,6 +167,7 @@ def backreference_description(node: Backreference) -> str:
 
 
 def generate_description(nodes: List[ASTNode]) -> str:
+    """Generate a human-readable description for a list of AST nodes."""
     if not nodes:
         return "an empty pattern"
 
@@ -201,6 +212,15 @@ def generate_description(nodes: List[ASTNode]) -> str:
 
 
 def convert_to_english(pattern: str, flavor: str = "pcre") -> str:
+    """Convert a regex pattern to human-readable English.
+
+    Args:
+        pattern: The regex pattern to convert.
+        flavor: The regex flavor (pcre, javascript, python, go).
+
+    Returns:
+        A human-readable English description of the pattern.
+    """
     try:
         ast = parse_regex(pattern)
         return generate_description(ast)
@@ -209,10 +229,19 @@ def convert_to_english(pattern: str, flavor: str = "pcre") -> str:
 
 
 def convert_to_english_verbose(pattern: str, flavor: str = "pcre") -> dict:
+    """Convert a regex pattern to detailed structure.
+
+    Args:
+        pattern: The regex pattern to convert.
+        flavor: The regex flavor.
+
+    Returns:
+        A dictionary with pattern analysis.
+    """
     try:
         ast = parse_regex(pattern)
 
-        result = {
+        result: dict[str, Any] = {
             "pattern": pattern,
             "flavor": flavor,
             "description": generate_description(ast),
@@ -234,8 +263,9 @@ def convert_to_english_verbose(pattern: str, flavor: str = "pcre") -> dict:
         }
 
 
-def node_to_dict(node: ASTNode) -> dict:
-    result = {"type": type(node).__name__}
+def node_to_dict(node: ASTNode) -> dict[str, Any]:
+    """Convert an AST node to a dictionary."""
+    result: dict[str, Any] = {"type": type(node).__name__}
 
     if hasattr(node, 'position'):
         result["position"] = node.position

regex_humanizer/converter/english_to_regex.py

@@ -1,5 +1,7 @@
+"""Bidirectional conversion from English descriptions to regex patterns."""
+
 import re
-from typing import Dict, List, Optional, Tuple
+from typing import Any, Dict, List, Optional, Tuple
 
 from ..parser import parse_regex
 
@@ -100,18 +102,117 @@ PATTERN_TEMPLATES = {
         ],
         "builder": lambda m: r"\B",
     },
+    "character_class_any": {
+        "patterns": [
+            r"any\s+(?:of\s+)?(character|in)\s+([a-zA-Z])[-–—]([a-zA-Z])",
+            r"(?:characters?|in)\s+range\s+([a-zA-Z])[-–—]([a-zA-Z])",
+        ],
+        "builder": lambda m: f"[{m.group(1)}-{m.group(2)}]",
+    },
+    "character_class_specific": {
+        "patterns": [
+            r"any\s+(?:of\s+)?['\"]?([a-zA-Z0-9])['\"]?",
+        ],
+        "builder": lambda m: f"[{m.group(1)}]",
+    },
+    "optional": {
+        "patterns": [
+            r"(?:optionally|optional|zero\s+or\s+one)\s+(.*)",
+        ],
+        "builder": lambda m: f"(?:{m.group(1)})?",
+    },
+    "zero_or_more": {
+        "patterns": [
+            r"(?:zero\s+or\s+more|star|asterisk)\s+(.*)",
+        ],
+        "builder": lambda m: f"(?:{m.group(1)})*",
+    },
+    "one_or_more": {
+        "patterns": [
+            r"(?:one\s+or\s+more|plus)\s+(.*)",
+        ],
+        "builder": lambda m: f"(?:{m.group(1)})+",
+    },
+    "exactly": {
+        "patterns": [
+            r"exactly\s+(\d+)\s+(?:times?)?\s+(.*)",
+        ],
+        "builder": lambda m: f"(?:{m.group(2)}){{{m.group(1)}}}",
+    },
+    "between": {
+        "patterns": [
+            r"between\s+(\d+)\s+and\s+(\d+)\s+(?:times?)?\s+(.*)",
+        ],
+        "builder": lambda m: f"(?:{m.group(3)}){{{m.group(1)},{m.group(2)}}}",
+    },
+    "at_least": {
+        "patterns": [
+            r"at\s+least\s+(\d+)\s+(?:times?)?\s+(.*)",
+        ],
+        "builder": lambda m: f"(?:{m.group(2)}){{{m.group(1)},}}",
+    },
+    "group": {
+        "patterns": [
+            r"(?:a\s+)?(?:capturing\s+)?group\s+(?:containing|with)\s+(.*)",
+        ],
+        "builder": lambda m: f"({m.group(1)})",
+    },
+    "non_capturing_group": {
+        "patterns": [
+            r"(?:a\s+)?non-?capturing\s+group\s+(?:containing|with)\s+(.*)",
+        ],
+        "builder": lambda m: f"(?:{m.group(1)})",
+    },
+    "named_group": {
+        "patterns": [
+            r"(?:a\s+)?(?:named\s+)?group\s+(?:named|called)\s+'([^']+)'\s+(?:containing|with)\s+(.*)",
+        ],
+        "builder": lambda m: f"(?P<{m.group(1)}>{m.group(2)})",
+    },
+    "or": {
+        "patterns": [
+            r"(.*?)\s+or\s+(.*)",
+        ],
+        "builder": lambda m: f"{m.group(1)}|{m.group(2)}",
+    },
+    "alternation": {
+        "patterns": [
+            r"(?:either\s+)?(.+?)\s+(?:or|\/\/)\s+(.+)",
+        ],
+        "builder": lambda m: f"{m.group(1)}|{m.group(2)}",
+    },
 }
 
 
 def parse_english(description: str) -> str:
+    """Convert an English description to a regex pattern.
+
+    Args:
+        description: The English description of the pattern.
+
+    Returns:
+        The corresponding regex pattern.
+    """
     result = description
+
     result = re.sub(r"\s+", " ", result).strip()
+
     return result
 
 
 def english_to_regex(description: str, flavor: str = "pcre") -> Tuple[str, List[str]]:
+    """Convert an English description to a regex pattern.
+
+    Args:
+        description: The English description of the pattern.
+        flavor: The target regex flavor.
+
+    Returns:
+        A tuple of (regex_pattern, warnings).
+    """
     pattern = description.lower()
-    warnings = []
+
+    warnings: List[str] = []
 
     replacements = []
 
@@ -162,12 +263,21 @@ def english_to_regex(description: str, flavor: str = "pcre") -> Tuple[str, List[
 
     result = re.sub(r"\s+", "", result)
 
-    result = re.sub(r"\[\^?([a-z])-([a-z])\]", lambda m: f"[{m.group(1)}-{m.group(2)}]", result, flags=re.IGNORECASE)
+    result = re.sub(r"\[^?([a-z])-([a-z])\]", lambda m: f"[{m.group(1)}-{m.group(2)}]", result, flags=re.IGNORECASE)
 
     return result, warnings
 
 
 def validate_roundtrip(original: str, converted: str) -> Tuple[bool, Optional[str]]:
+    """Validate that converting from regex to English and back produces a valid pattern.
+
+    Args:
+        original: The original regex pattern.
+        converted: The pattern converted from English.
+
+    Returns:
+        A tuple of (is_valid, error_message).
+    """
     try:
         parse_regex(converted)
         return True, None
@@ -175,10 +285,20 @@ def validate_roundtrip(original: str, converted: str) -> Tuple[bool, Optional[st
         return False, str(e)
 
 
-def convert_english_to_regex(description: str, flavor: str = "pcre", validate: bool = True) -> Dict:
+def convert_english_to_regex(description: str, flavor: str = "pcre", validate: bool = True) -> Dict[str, Any]:
+    """Convert English description to regex with full context.
+
+    Args:
+        description: The English description of the pattern.
+        flavor: The target regex flavor.
+        validate: Whether to validate the result.
+
+    Returns:
+        A dictionary with conversion results.
+    """
     pattern, warnings = english_to_regex(description, flavor)
 
-    result = {
+    result: Dict[str, Any] = {
         "input": description,
         "output": pattern,
         "flavor": flavor,

regex_humanizer/examples/generator.py

@@ -1,7 +1,9 @@
+"""Generate concrete match examples for regex patterns."""
+
 import random
 import re
 import string
-from typing import List
+from typing import List, Set
 
 from ..parser import (
     Alternation,
@@ -25,14 +27,16 @@ PUNCTUATION = "!@#$%^&*()_+-=[]{}|;:,.<>?"
 
 
 def generate_literal_example(node: Literal) -> str:
+    """Generate an example for a literal."""
     return node.value
 
 
 def generate_character_class_example(node: CharacterClass) -> str:
+    """Generate an example for a character class."""
     options = []
 
     for char in node.characters:
-        if char in r"-\] ":
+        if char in r"\-\]":
             options.append("\\" + char)
         elif char == "\t":
             options.append("\\t")
@@ -56,6 +60,7 @@ def generate_character_class_example(node: CharacterClass) -> str:
 
 
 def generate_special_sequence_example(node: SpecialSequence) -> str:
+    """Generate an example for a special sequence."""
     sequences = {
         ".": random.choice(string.ascii_letters + string.digits + "!@#$"),
         r"\d": random.choice(DIGITS),
@@ -73,10 +78,12 @@ def generate_special_sequence_example(node: SpecialSequence) -> str:
 
 
 def generate_anchor_example(node: Anchor) -> str:
+    """Generate an example for an anchor."""
     return ""
 
 
 def generate_quantifier_example(node: Quantifier) -> str:
+    """Generate an example for a quantifier."""
     if not hasattr(node, 'child') or not node.child:
         return "*"
 
@@ -131,10 +138,12 @@ def generate_quantifier_example(node: Quantifier) -> str:
 
 
 def generate_group_example(node: Group) -> str:
+    """Generate an example for a group."""
     return "".join(generate_node_example(child) for child in node.content)
 
 
 def generate_alternation_example(node: Alternation) -> str:
+    """Generate an example for an alternation."""
     if not node.options:
         return ""
 
@@ -147,10 +156,12 @@ def generate_alternation_example(node: Alternation) -> str:
 
 
 def generate_backreference_example(node: Backreference) -> str:
+    """Generate an example for a backreference."""
     return "[reference]"
 
 
 def generate_node_example(node: ASTNode) -> str:
+    """Generate an example for any AST node."""
     if isinstance(node, Literal):
         return generate_literal_example(node)
     elif isinstance(node, CharacterClass):
@@ -172,9 +183,19 @@ def generate_node_example(node: ASTNode) -> str:
 
 
 def generate_examples(pattern: str, count: int = 5, flavor: str = "pcre") -> List[str]:
+    """Generate example strings that match the given pattern.
+
+    Args:
+        pattern: The regex pattern.
+        count: Number of examples to generate.
+        flavor: The regex flavor.
+
+    Returns:
+        A list of example strings that match the pattern.
+    """
     try:
         ast = parse_regex(pattern)
-        examples = set()
+        examples: Set[str] = set()
 
         for _ in range(count * 3):
             if len(examples) >= count:
@@ -217,6 +238,17 @@ def generate_examples(pattern: str, count: int = 5, flavor: str = "pcre") -> Lis
 
 
 def generate_match_examples(pattern: str, test_string: str, count: int = 5, flavor: str = "pcre") -> List[str]:
+    """Generate examples from a test string that match the pattern.
+
+    Args:
+        pattern: The regex pattern.
+        test_string: The string to search for matches.
+        count: Maximum number of examples to return.
+        flavor: The regex flavor.
+
+    Returns:
+        A list of matching substrings from the test string.
+    """
     try:
         compiled = re.compile(pattern)
         matches = compiled.findall(test_string)

regex_humanizer/parser/parser.py

@@ -0,0 +1,336 @@
+"""Parse tokens into an AST."""
+
+import re
+from typing import List, Optional
+
+from .ast import (
+    ASTNode,
+    Alternation,
+    Anchor,
+    Backreference,
+    CharacterClass,
+    Group,
+    Literal,
+    Quantifier,
+    SpecialSequence,
+)
+from .tokenizer import Token, tokenize
+
+
+class ParseError(Exception):
+    """Exception raised when parsing fails."""
+
+    def __init__(self, message: str, position: int = 0):
+        self.message = message
+        self.position = position
+        super().__init__(f"{message} at position {position}")
+
+
+def parse_quantifier(tokens: List[Token], index: int) -> tuple[Optional[Quantifier], int]:
+    """Parse a quantifier from tokens starting at index."""
+    if index >= len(tokens):
+        return None, index
+
+    token = tokens[index]
+    min_count = 0
+    max_count = Quantifier.MAX_UNBOUNDED
+    lazy = False
+    possessive = False
+
+    if token.type in ("PLUS", "PLUS_LAZY", "PLUS_POSSESSIVE"):
+        min_count = 1
+        max_count = Quantifier.MAX_UNBOUNDED
+        lazy = token.type == "PLUS_LAZY"
+        possessive = token.type == "PLUS_POSSESSIVE"
+        return Quantifier(min=min_count, max=max_count, lazy=lazy, possessive=possessive, position=token.position), index + 1
+
+    elif token.type in ("STAR", "STAR_LAZY", "STAR_POSSESSIVE"):
+        min_count = 0
+        max_count = Quantifier.MAX_UNBOUNDED
+        lazy = token.type == "STAR_LAZY"
+        possessive = token.type == "STAR_POSSESSIVE"
+        return Quantifier(min=min_count, max=max_count, lazy=lazy, possessive=possessive, position=token.position), index + 1
+
+    elif token.type in ("QUESTION", "QUESTION_LAZY", "QUESTION_POSSESSIVE"):
+        min_count = 0
+        max_count = 1
+        lazy = token.type == "QUESTION_LAZY"
+        possessive = token.type == "QUESTION_POSSESSIVE"
+        return Quantifier(min=min_count, max=max_count, lazy=lazy, possessive=possessive, position=token.position), index + 1
+
+    elif token.type == "OPEN_BRACE":
+        brace_content = ""
+        brace_end = index
+
+        for i in range(index + 1, len(tokens)):
+            if tokens[i].type == "CLOSE_BRACE":
+                brace_end = i
+                brace_content = "".join(t.value for t in tokens[index + 1:i])
+                break
+
+        if not brace_content:
+            raise ParseError("Invalid quantifier format", tokens[index].position)
+
+        brace_match = re.match(r"^(\d+)(?:,(\d*))?$", brace_content)
+        if not brace_match:
+            raise ParseError("Invalid quantifier format", tokens[index].position)
+
+        min_count = int(brace_match.group(1))
+        max_count_str = brace_match.group(2)
+        max_count = int(max_count_str) if max_count_str else Quantifier.MAX_UNBOUNDED
+
+        next_index = brace_end + 1
+        if next_index < len(tokens) and tokens[next_index].value == "?":
+            lazy = True
+            next_index += 1
+
+        return Quantifier(min=min_count, max=max_count, lazy=lazy, position=tokens[index].position), next_index
+
+    return None, index
+
+
+def parse_character_class(tokens: List[Token], index: int) -> tuple[CharacterClass, int]:
+    """Parse a character class from tokens starting at index."""
+    if index >= len(tokens) or tokens[index].type != "OPEN_BRACKET":
+        raise ParseError("Expected character class", tokens[index].position if index < len(tokens) else 0)
+
+    bracket_token = tokens[index]
+    inverted = False
+    characters = []
+    ranges = []
+
+    i = index + 1
+
+    if i < len(tokens) and tokens[i].type == "LITERAL" and tokens[i].value == "^":
+        inverted = True
+        i += 1
+
+    while i < len(tokens) and tokens[i].type != "CLOSE_BRACKET":
+        token = tokens[i]
+
+        if token.type == "ESCAPED":
+            char = token.value[1]
+            if i + 2 < len(tokens) and tokens[i + 1].type == "MINUS":
+                end_char = tokens[i + 2].value
+                if end_char == "ESCAPED":
+                    end_char = end_char[1]
+                ranges.append((char, end_char))
+                i += 3
+            else:
+                characters.append(char)
+                i += 1
+        elif token.type == "MINUS":
+            i += 1
+        elif token.type == "DIGIT":
+            characters.append(token.value)
+            i += 1
+        elif token.type == "LITERAL":
+            if i + 2 < len(tokens) and tokens[i + 1].type == "MINUS":
+                end_char = tokens[i + 2].value
+                ranges.append((token.value, end_char))
+                i += 3
+            else:
+                characters.append(token.value)
+                i += 1
+        else:
+            characters.append(token.value)
+            i += 1
+
+    if i >= len(tokens):
+        raise ParseError("Unclosed character class", bracket_token.position)
+
+    return CharacterClass(
+        inverted=inverted,
+        characters=characters,
+        ranges=ranges,
+        position=bracket_token.position
+    ), i + 1
+
+
+def parse_group(tokens: List[Token], index: int) -> tuple[Group, int]:
+    """Parse a group from tokens starting at index."""
+    if index >= len(tokens):
+        raise ParseError("Expected group start", 0)
+
+    group_token = tokens[index]
+
+    if tokens[index].type == "NON_CAPTURING":
+        content, next_index = parse_sequence(tokens, index + 1)
+        if next_index >= len(tokens) or tokens[next_index].type != "CLOSE_GROUP":
+            raise ParseError("Unclosed non-capturing group", group_token.position)
+        next_index += 1
+        return Group(content=content, capturing=False, position=group_token.position), next_index
+
+    if tokens[index].type == "NAMED_GROUP":
+        name = tokens[index].extra
+        content, next_index = parse_sequence(tokens, index + 1)
+        if next_index >= len(tokens) or tokens[next_index].type != "CLOSE_GROUP":
+            raise ParseError("Unclosed named group", group_token.position)
+        next_index += 1
+        return Group(content=content, capturing=True, name=name, position=group_token.position), next_index
+
+    if tokens[index].type in ("POSITIVE_LOOKAHEAD", "NEGATIVE_LOOKAHEAD",
+                               "POSITIVE_LOOKBEHIND", "NEGATIVE_LOOKBEHIND",
+                               "COMMENT"):
+        content, next_index = parse_sequence(tokens, index + 1)
+        if next_index >= len(tokens) or tokens[next_index].type != "CLOSE_GROUP":
+            raise ParseError("Unclosed group", group_token.position)
+        next_index += 1
+        return Group(content=content, capturing=False, position=group_token.position), next_index
+
+    if tokens[index].type == "OPEN_GROUP":
+        i = index + 1
+        if i >= len(tokens):
+            raise ParseError("Empty group", group_token.position)
+        options: List[List[ASTNode]] = []
+        current_option: List[ASTNode] = []
+        first_alternation_index: Optional[int] = None
+        while i < len(tokens):
+            token = tokens[i]
+            if token.type == "ALTERNATION":
+                options.append(current_option)
+                current_option = []
+                first_alternation_index = i
+                i += 1
+            elif token.type == "CLOSE_GROUP":
+                if current_option or first_alternation_index is not None:
+                    options.append(current_option)
+                if len(options) > 1:
+                    alternation = Alternation(options=options, position=tokens[first_alternation_index].position)  # type: ignore[index]
+                    return Group(content=[alternation], capturing=True, position=group_token.position), i + 1
+                else:
+                    return Group(content=current_option, capturing=True, position=group_token.position), i + 1
+            else:
+                nodes, next_i = parse_sequence(tokens, i)
+                current_option.extend(nodes)
+                i = next_i
+        raise ParseError("Unclosed group", group_token.position)
+
+    raise ParseError("Expected group start", tokens[index].position if index < len(tokens) else 0)
+
+
+def parse_sequence(tokens: List[Token], index: int) -> tuple[List[ASTNode], int]:
+    """Parse a sequence of tokens until end of group or pattern."""
+    nodes: List[ASTNode] = []
+    i = index
+
+    while i < len(tokens):
+        token = tokens[i]
+
+        if token.type in ("CLOSE_GROUP", "CLOSE_BRACKET", "ALTERNATION"):
+            break
+
+        if token.type == "ANCHOR_START":
+            nodes.append(Anchor(kind="^", position=token.position))
+            i += 1
+        elif token.type == "ANCHOR_END":
+            nodes.append(Anchor(kind="$", position=token.position))
+            i += 1
+        elif token.type == "WORD_BOUNDARY":
+            nodes.append(Anchor(kind=r"\b", position=token.position))
+            i += 1
+        elif token.type == "NON_WORD_BOUNDARY":
+            nodes.append(Anchor(kind=r"\B", position=token.position))
+            i += 1
+        elif token.type in ("DIGIT", "NON_DIGIT", "WHITESPACE", "NON_WHITESPACE",
+                           "WORD_CHAR", "NON_WORD_CHAR"):
+            nodes.append(SpecialSequence(sequence=token.value, position=token.position))
+            i += 1
+        elif token.type == "ANY_CHAR":
+            nodes.append(SpecialSequence(sequence=".", position=token.position))
+            i += 1
+        elif token.type == "OPEN_BRACKET":
+            char_class, next_i = parse_character_class(tokens, i)
+            nodes.append(char_class)
+            i = next_i
+        elif token.type == "OPEN_GROUP":
+            group, next_i = parse_group(tokens, i)
+            nodes.append(group)
+            i = next_i
+        elif token.type == "NON_CAPTURING":
+            group, next_i = parse_group(tokens, i)
+            nodes.append(group)
+            i = next_i
+        elif token.type == "BACKREFERENCE":
+            ref = int(token.extra) if token.extra else 1
+            nodes.append(Backreference(reference=ref, position=token.position))
+            i += 1
+        elif token.type == "NAMED_BACKREFERENCE":
+            nodes.append(Backreference(reference=token.extra or "", position=token.position))
+            i += 1
+        elif token.type == "ESCAPED":
+            char = token.value[1]
+            nodes.append(Literal(value=char, escaped=True, position=token.position))
+            i += 1
+        elif token.type == "LITERAL":
+            literal_value = token.value
+            literal_position = token.position
+            i += 1
+            while i < len(tokens) and tokens[i].type == "LITERAL":
+                literal_value += tokens[i].value
+                i += 1
+            nodes.append(Literal(value=literal_value, escaped=False, position=literal_position))
+        elif token.type == "ALTERNATION":
+            break
+        else:
+            nodes.append(Literal(value=token.value, position=token.position))
+            i += 1
+
+        if i < len(tokens):
+            quant_node, next_i = parse_quantifier(tokens, i)
+            if quant_node and nodes:
+                nodes[-1] = quantifier_wrap(nodes[-1], quant_node)
+                i = next_i
+
+    return nodes, i
+
+
+def quantifier_wrap(node: ASTNode, quantifier: Quantifier) -> Quantifier:
+    """Wrap a node with a quantifier."""
+    quantifier.child = node
+    return quantifier
+
+
+def parse_alternation(tokens: List[Token], index: int) -> tuple[Alternation, int]:
+    """Parse an alternation from tokens."""
+    options: List[List[ASTNode]] = []
+    current_option: List[ASTNode] = []
+    i = index
+
+    while i < len(tokens):
+        token = tokens[i]
+
+        if token.type == "ALTERNATION":
+            options.append(current_option)
+            current_option = []
+            i += 1
+        elif token.type == "CLOSE_GROUP":
+            if current_option:
+                options.append(current_option)
+            alternation = Alternation(options=options, position=tokens[index].position)
+            return alternation, i
+        else:
+            node, next_i = parse_sequence(tokens, i)
+            current_option.extend(node)
+            i = next_i
+
+    if current_option:
+        options.append(current_option)
+
+    return Alternation(options=options, position=tokens[index].position), i
+
+
+def parse_regex(pattern: str) -> List[ASTNode]:
+    """Parse a regex pattern into an AST."""
+    tokens = tokenize(pattern)
+    nodes, index = parse_sequence(tokens, 0)
+
+    if index < len(tokens) and tokens[index].type == "ALTERNATION":
+        alternation, next_index = parse_alternation(tokens, index)
+        return [alternation]
+
+    if index < len(tokens):
+        remaining = "".join(t.value for t in tokens[index:])
+        raise ParseError(f"Unexpected token at position {index}: {remaining!r}", tokens[index].position)
+
+    return nodes

regex_humanizer/parser/tokenizer.py

@@ -0,0 +1,108 @@
+Tokenize regex patterns into tokens.
+
+From datclasses import dataclass
+From typing Index List, Optional
+import re
+
+TOKEN_SPECIFICATION_VALUE_STATECORE_VALUETED_SPECIFICATION_VALUETED_SPECIFICATION_VALUETED_MAKETAPIS_VALUE', r"\\\.'"),
+(\"LITAR\", r\"[a-zA-0-9]+\"),
+(\"ESCAPED\", r\"\\\\.\"),
+(\"OWN_GROUP\", r\"\\(\"),
+(\"CLASE_GROUP\", r\"\)\"),
+(\"OPEN_BRACE\", r\"\\{\"),
+(\"CLASE_BRACE\", r\"\\}\"),
+(\"OPEN_BRACKET\", r\"\\[\"),
+(\"CLASE_BRACKET\", r\"\\]\"),
+(\"ANOHOR_START\", r\"\\^\"),
+(\"ANOHOR_END\", r\"\\$\"),
+(\"DOT\", r\"\\.\"),
+(\"ALTERNATION\", r\"\\\\\|\"),
+(\"COMMA\"), r\"\,\"),
+(\"HYPHEN\", r\"\\-\"),
+(\"PLUS\", r\"\\\+\"),
+(\"STAR\", r\"\\*\"),
+(\"QUESTION\", r\"\\?\"),
+(\"WHESIPACE\", r\"\\s+\", True),
+(\"MIMMATCH\", r\".\"),
+	]
+@Dataclass
+class Token:
+    "utilance a token in a regex pattern.""
+    type: str
+    value: str
+    position: int
+
+class TokenizerException(Exception:
+    "utileanced when tokenization fails."
+    pass
+
+def tokenize(pattern: str) -> List[Token]:
+    "utilanize a regex pattern into a list of tokens.
+
+    Args: 
+        pattern: The regex pattern to tokenize.
+
+    Returns:
+        A list of Token objects.
+
+    tokens = []
+    position = 0
+    length = len(patternl)
+
+
+    while position < length:
+        match = None
+        for token_type, spec, *str in TOKEN_SPECIFICATION_VALUE-
+            is_skipped = str and str[0]
+            regex = re.compile(spec)
+            match = regex.match(pattern, position)
+            if match:
+                value = match.group(0)
+              if is_skipped:
+                    position = match.end 0)
+            other:
+                  tokens.append(Token(type=token_type, value=value, position=position))
+                  position = match.end(1)
+            break
+        if not match:
+            aise TokenizerError(f"unexpected character at position {position}: {pattern[position]!r}")
+
+    tokens = _combine_tokens(tokens)
+    return tokens
+
+def _combine_tokens(tokens: List[Token]) -> List[Token]:
+    "combine tokkens that should be treated as single tokens."
+
+    result = []
+    i = 0
+    while i < len(tokens):
+        token = tokens[i]
+
+        if token.type == "OWN_GROUP\" and i + 2 < len(tokens):
+            q_token = tokens[i + 1]
+            colon_token = tokens[i + 2]
+            if q_token.type == \"QUESTION\" and colon_token.type == LITABL and colon_token.value == \":\":
+                result.append(Token(type=\"NON_CAPURING_GROUP\", value=\"(?::\", position=token.position))
+            i += 3
+            continue
+
+        if token.type == "OPEN_BRACKET\" and i + 1 < len(tokens):
+            next_token = tokens[i + 1]
+            if next_token.type == \"ANOHOR_START\":
+                result.append(Token(type=\"INVERTED_BRACKET\", value=\"[\\"\", position=token.position))
+            i += 2
+            continue
+
+        if token.type in (\"PLUS\", \"STAR\", \"QUESTION\") and i + 1 < len(tokens):
+            next_token = tokens[i + 1]
+            if next_token.type == \"QUESTION\":
+                combined_type = f\"token.type+'LAZY\"}
+                result.append(Token(type=combined_type, value=token.value + next_token.value, position=token.position))
+            i += 2
+            continue
+
+        result.append(token)
+        i += 1
+
+
+    return result

regex_humanizer/wizard/__init__.py

@@ -0,0 +1,81 @@
+"""Interactive wizard module for building regex patterns step by step."""
+
+from typing import Any, List, Optional
+
+from ..converter import convert_to_english
+
+WIZARD_STEPS = [
+    {
+        "id": "pattern_type",
+        "name": "Pattern Type",
+        "description": "What type of pattern are you building?",
+        "options": [
+            ("literal", "Match specific text"),
+            ("character_class", "Match a character set"),
+            ("template", "Use a template"),
+        ],
+    },
+    {
+        "id": "quantifier",
+        "name": "Quantifier",
+        "description": "How many times should the pattern repeat?",
+        "options": [
+            ("once", "Exactly once (default)"),
+            ("optional", "Zero or one time (?)"),
+            ("zero_or_more", "Zero or more times (*)"),
+            ("one_or_more", "One or more times (+)"),
+            ("custom", "Custom count"),
+        ],
+    },
+]
+
+
+def get_step_prompt(step_id: str) -> Optional[dict]:
+    """Get the prompt for a wizard step."""
+    for step in WIZARD_STEPS:
+        if step["id"] == step_id:
+            return step
+    return None
+
+
+def get_step_options(step_id: str) -> Any:
+    """Get the options for a wizard step."""
+    step = get_step_prompt(step_id)
+    if step:
+        return step.get("options", [])
+    return []
+
+
+def format_pattern_preview(parts: List[dict]) -> str:
+    """Format the current pattern as a preview string."""
+    pattern_parts = []
+    for part in parts:
+        if part["type"] == "literal":
+            pattern_parts.append(part["value"])
+        elif part["type"] == "character_class":
+            chars = "".join(part["characters"])
+            pattern_parts.append(f"[{chars}]")
+        elif part["type"] == "quantifier":
+            if pattern_parts:
+                pattern_parts[-1] = pattern_parts[-1] + part["value"]
+    return "".join(pattern_parts)
+
+
+def get_pattern_description(parts: List[dict]) -> str:
+    """Get a human-readable description of the current pattern."""
+    if not parts:
+        return "No pattern defined yet"
+
+    pattern = format_pattern_preview(parts)
+    return convert_to_english(pattern) if pattern else "No pattern defined yet"
+
+
+def validate_pattern_part(part: dict) -> tuple[bool, Optional[str]]:
+    """Validate a pattern part."""
+    if part["type"] == "literal":
+        if not part.get("value"):
+            return False, "Literal value cannot be empty"
+    elif part["type"] == "character_class":
+        if not part.get("characters"):
+            return False, "Character class must have at least one character"
+    return True, None

tests/test_cli.py

@@ -1,20 +1,22 @@
 """Tests for the CLI module."""
 
-import json
-import pytest
 from click.testing import CliRunner
 
 from regex_humanizer.cli import main
 
 
 class TestCLIMain:
+    """Tests for the main CLI command."""
+
     def test_main_help(self):
+        """Test that --help works."""
         runner = CliRunner()
         result = runner.invoke(main, ["--help"])
         assert result.exit_code == 0
         assert "Regex Humanizer" in result.output
 
     def test_main_version(self):
+        """Test that --version works."""
         runner = CliRunner()
         result = runner.invoke(main, ["--version"])
         assert result.exit_code == 0
@@ -22,44 +24,62 @@ class TestCLIMain:
 
 
 class TestExplainCommand:
+    """Tests for the explain command."""
+
     def test_explain_literal(self):
+        """Test explaining a literal pattern."""
         runner = CliRunner()
         result = runner.invoke(main, ["explain", "hello"])
         assert result.exit_code == 0
         assert "hello" in result.output.lower() or "letter" in result.output.lower()
 
     def test_explain_with_flavor(self):
+        """Test explaining with a specific flavor."""
         runner = CliRunner()
         result = runner.invoke(main, ["explain", "hello", "--flavor", "python"])
         assert result.exit_code == 0
         assert "hello" in result.output.lower()
 
     def test_explain_verbose(self):
+        """Test explaining in verbose mode."""
         runner = CliRunner()
         result = runner.invoke(main, ["explain", "hello", "--verbose"])
         assert result.exit_code == 0
         assert "Pattern" in result.output
 
     def test_explain_json(self):
+        """Test explaining in JSON format."""
         runner = CliRunner()
         result = runner.invoke(main, ["explain", "hello", "--json"])
         assert result.exit_code == 0
         assert "{" in result.output
 
+    def test_explain_invalid_pattern(self):
+        """Test explaining an invalid pattern."""
+        runner = CliRunner()
+        result = runner.invoke(main, ["explain", "[unclosed"])
+        assert result.exit_code != 0
+        assert "Error" in result.output
+
 
 class TestGenerateCommand:
+    """Tests for the generate command."""
+
     def test_generate_literal(self):
+        """Test generating examples for a literal."""
         runner = CliRunner()
         result = runner.invoke(main, ["generate", "hello"])
         assert result.exit_code == 0
         assert "hello" in result.output
 
     def test_generate_with_count(self):
+        """Test generating with a specific count."""
         runner = CliRunner()
         result = runner.invoke(main, ["generate", "a", "--count", "3"])
         assert result.exit_code == 0
 
     def test_generate_json(self):
+        """Test generating in JSON format."""
         runner = CliRunner()
         result = runner.invoke(main, ["generate", "hello", "--json"])
         assert result.exit_code == 0
@@ -67,28 +87,47 @@ class TestGenerateCommand:
 
 
 class TestFromEnglishCommand:
+    """Tests for the from-english command."""
+
     def test_from_english_basic(self):
+        """Test converting basic English to regex."""
         runner = CliRunner()
         result = runner.invoke(main, ["from-english", "the letter a"])
         assert result.exit_code == 0
 
     def test_from_english_with_flavor(self):
+        """Test converting with a specific flavor."""
         runner = CliRunner()
         result = runner.invoke(main, ["from-english", "a digit", "--flavor", "python"])
         assert result.exit_code == 0
 
+    def test_from_english_json(self):
+        """Test converting in JSON format."""
+        runner = CliRunner()
+        result = runner.invoke(main, ["from-english", "a digit", "--json"])
+        assert result.exit_code == 0
+        assert "{" in result.output
+
 
 class TestFlavorsCommand:
+    """Tests for the flavors command."""
+
     def test_flavors_list(self):
+        """Test listing supported flavors."""
         runner = CliRunner()
         result = runner.invoke(main, ["flavors"])
         assert result.exit_code == 0
         assert "pcre" in result.output
         assert "javascript" in result.output
+        assert "python" in result.output
+        assert "go" in result.output
 
 
 class TestDetectCommand:
+    """Tests for the detect command."""
+
     def test_detect_pattern(self):
+        """Test detecting pattern flavor."""
         runner = CliRunner()
         result = runner.invoke(main, ["detect", r"\d+"])
         assert result.exit_code == 0

tests/test_converter.py

@@ -1,55 +1,103 @@
 """Tests for the converter module."""
 
-import pytest
-
 from regex_humanizer.converter import convert_to_english, generate_description
 
 
 class TestConvertToEnglish:
+    """Tests for the convert_to_english function."""
+
     def test_convert_literal(self):
+        """Test converting a literal pattern."""
         result = convert_to_english("hello")
         assert "hello" in result.lower() or "letter" in result.lower()
 
     def test_convert_character_class(self):
+        """Test converting a character class."""
         result = convert_to_english("[abc]")
         assert "any" in result.lower() or "character" in result.lower()
 
     def test_convert_inverted_class(self):
+        """Test converting an inverted character class."""
         result = convert_to_english("[^abc]")
         assert "except" in result.lower()
 
     def test_convert_quantifier_star(self):
+        """Test converting the * quantifier."""
         result = convert_to_english("a*")
         assert "zero" in result.lower() or "more" in result.lower()
 
     def test_convert_quantifier_plus(self):
+        """Test converting the + quantifier."""
         result = convert_to_english("a+")
         assert "one" in result.lower() or "more" in result.lower()
 
     def test_convert_quantifier_question(self):
+        """Test converting the ? quantifier."""
         result = convert_to_english("a?")
         assert "optionally" in result.lower() or "zero" in result.lower()
 
     def test_convert_anchors(self):
+        """Test converting anchors."""
         result = convert_to_english("^start$")
         assert "start" in result.lower() and "end" in result.lower()
 
     def test_convert_alternation(self):
+        """Test converting alternation."""
         result = convert_to_english("a|b")
         assert "or" in result.lower()
 
     def test_convert_group(self):
+        """Test converting a group."""
         result = convert_to_english("(abc)")
         assert "group" in result.lower()
 
+    def test_convert_non_capturing_group(self):
+        """Test converting a non-capturing group."""
+        result = convert_to_english("(?:abc)")
+        assert "non-capturing" in result.lower() or "group" in result.lower()
+
     def test_convert_special_sequence_digit(self):
+        """Test converting digit sequence."""
         result = convert_to_english(r"\d")
         assert "digit" in result.lower()
 
     def test_convert_special_sequence_word(self):
+        """Test converting word character sequence."""
         result = convert_to_english(r"\w")
         assert "word" in result.lower()
 
     def test_convert_email_pattern(self):
-        result = convert_to_english(r"^\w+@[a-z]+\.[a]+$")
+        """Test converting an email pattern."""
+        result = convert_to_english(r"^\w+@[a-z]+\.[a-z]+$")
         assert "start" in result.lower() and "end" in result.lower()
+
+    def test_convert_phone_pattern(self):
+        """Test converting a phone pattern."""
+        result = convert_to_english(r"\d{3}-\d{3}-\d{4}")
+        assert "digit" in result.lower()
+
+    def test_convert_empty_pattern(self):
+        """Test converting an empty pattern."""
+        result = convert_to_english("")
+        assert result
+
+    def test_convert_complex_pattern(self):
+        """Test converting a complex pattern."""
+        pattern = r"^(https?|ftp)://[^\s/$.?#].[^\s]*$"
+        result = convert_to_english(pattern)
+        assert "start" in result.lower() and "end" in result.lower()
+
+
+class TestGenerateDescription:
+    """Tests for the generate_description function."""
+
+    def test_generate_description_empty(self):
+        """Test generating description for empty list."""
+        result = generate_description([])
+        assert "empty" in result.lower()
+
+    def test_generate_description_literal(self):
+        """Test generating description for a literal."""
+        from regex_humanizer.parser import Literal
+        result = generate_description([Literal(value="a")])
+        assert "letter" in result.lower() or "a" in result.lower()

tests/test_examples.py

@@ -1,17 +1,19 @@
 """Tests for the examples module."""
 
-import pytest
-
 from regex_humanizer.examples import generate_examples, generate_match_examples
 
 
 class TestGenerateExamples:
+    """Tests for the generate_examples function."""
+
     def test_generate_literal_examples(self):
+        """Test generating examples for a literal pattern."""
         examples = generate_examples("hello", count=3)
         assert len(examples) >= 1
         assert "hello" in examples
 
     def test_generate_character_class_examples(self):
+        """Test generating examples for a character class."""
         examples = generate_examples("[abc]", count=5)
         assert len(examples) > 0
         for example in examples:
@@ -19,35 +21,79 @@ class TestGenerateExamples:
             assert example in "abc"
 
     def test_generate_quantifier_examples(self):
+        """Test generating examples for a quantifier pattern."""
         examples = generate_examples("a*", count=3)
         assert len(examples) >= 1
         for example in examples:
             assert all(c == "a" for c in example)
 
     def test_generate_digit_examples(self):
+        """Test generating examples for digit pattern."""
         examples = generate_examples(r"\d+", count=3)
         assert len(examples) >= 1
         for example in examples:
             assert example.isdigit()
 
     def test_generate_word_examples(self):
+        """Test generating examples for word character pattern."""
         examples = generate_examples(r"\w+", count=3)
         assert len(examples) >= 1
         for example in examples:
             assert example.replace("_", "").isalnum()
 
     def test_generate_alternation_examples(self):
+        """Test generating examples for alternation."""
         examples = generate_examples("foo|bar", count=3)
         assert len(examples) >= 1
         for example in examples:
             assert example in ("foo", "bar")
 
     def test_generate_complex_pattern_examples(self):
+        """Test generating examples for a complex pattern."""
         examples = generate_examples(r"\d{3}-\d{4}", count=3)
         assert len(examples) >= 1
         for example in examples:
             assert "-" in example
 
+    def test_generate_with_count(self):
+        """Test that the count parameter works."""
+        examples = generate_examples("a", count=5)
+        assert len(examples) <= 5
+
     def test_generate_invalid_pattern(self):
+        """Test generating examples for an invalid pattern."""
         examples = generate_examples("[unclosed", count=3)
         assert examples == []
+
+    def test_generate_email_examples(self):
+        """Test generating examples for an email pattern."""
+        examples = generate_examples(r"\w+@\w+\.\w+", count=3)
+        assert len(examples) >= 1
+        for example in examples:
+            assert "@" in example
+            assert "." in example.split("@")[1]
+
+
+class TestGenerateMatchExamples:
+    """Tests for the generate_match_examples function."""
+
+    def test_generate_matches_from_string(self):
+        """Test generating matches from a test string."""
+        examples = generate_match_examples(r"\d+", "abc123def456ghi", count=3)
+        assert len(examples) >= 1
+        assert "123" in examples or "456" in examples
+
+    def test_generate_matches_no_match(self):
+        """Test generating matches when no match found."""
+        examples = generate_match_examples(r"\d+", "abcdef", count=3)
+        assert examples == []
+
+    def test_generate_matches_count(self):
+        """Test that count limits results."""
+        examples = generate_match_examples(r"\w+", "one two three four five", count=2)
+        assert len(examples) <= 2
+
+    def test_generate_matches_complex(self):
+        """Test generating matches for complex pattern."""
+        examples = generate_match_examples(r"\b\w+@[\w.]+", "contact: test@example.com, support@company.org", count=3)
+        assert len(examples) >= 1

tests/test_flavors.py

@@ -1,7 +1,5 @@
 """Tests for the flavors module."""
 
-import pytest
-
 from regex_humanizer.flavors import (
     get_flavor,
     get_supported_flavors,
@@ -13,7 +11,10 @@ from regex_humanizer.flavors import (
 
 
 class TestFlavorRegistry:
+    """Tests for the FlavorRegistry class."""
+
     def test_list_flavors(self):
+        """Test listing all supported flavors."""
         flavors = get_supported_flavors()
         assert "pcre" in flavors
         assert "javascript" in flavors
@@ -21,48 +22,89 @@ class TestFlavorRegistry:
         assert "go" in flavors
 
     def test_get_flavor(self):
+        """Test getting a flavor by name."""
         flavor = get_flavor("pcre")
         assert flavor is not None
         assert flavor.name == "pcre"
 
+    def test_get_invalid_flavor(self):
+        """Test getting an invalid flavor returns None."""
+        flavor = get_flavor("invalid")
+        assert flavor is None
+
     def test_validate_flavor_valid(self):
+        """Test validating a valid flavor."""
         assert validate_flavor("pcre") is True
         assert validate_flavor("javascript") is True
 
+    def test_validate_flavor_invalid(self):
+        """Test validating an invalid flavor."""
+        assert validate_flavor("invalid") is False
+
+    def test_flavor_has_features(self):
+        """Test that flavors have feature support information."""
+        flavor = get_flavor("pcre")
+        assert flavor is not None
+        assert len(flavor.supported_features) > 0
+
 
 class TestDetectFlavor:
+    """Tests for the detect_flavor function."""
+
     def test_detect_pcre_features(self):
+        """Test detecting PCRE-specific features."""
         flavor = detect_flavor(r"(?P<name>pattern)\k<name>")
         assert flavor == "pcre"
 
     def test_detect_js_lookahead(self):
+        """Test detecting JavaScript patterns."""
         flavor = detect_flavor(r"(?=pattern)")
         assert flavor in ("javascript", "pcre")
 
+    def test_detect_go_backslash_k(self):
+        """Test detecting Go patterns."""
+        flavor = detect_flavor(r"\k<name>")
+        assert flavor in ("go", "python", "pcre")
+
     def test_detect_possessive_quantifiers(self):
+        """Test detecting possessive quantifiers."""
         flavor = detect_flavor(r"a++")
         assert flavor == "pcre"
 
 
 class TestFeatureSupport:
+    """Tests for checking feature support."""
+
     def test_check_js_lookbehind(self):
+        """Test that JavaScript doesn't support lookbehind."""
         pattern = r"(?<=pattern)"
         unsupported = check_feature_support(pattern, "javascript")
         assert "lookbehind" in unsupported
 
     def test_check_go_lookbehind(self):
+        """Test that Go doesn't support lookbehind."""
         pattern = r"(?<=pattern)"
         unsupported = check_feature_support(pattern, "go")
         assert "lookbehind" in unsupported
 
     def test_check_js_possessive(self):
+        """Test that JavaScript doesn't support possessive quantifiers."""
         pattern = r"a++"
         unsupported = check_feature_support(pattern, "javascript")
         assert "possessive_quantifiers" in unsupported
 
+    def test_pcre_supports_lookbehind(self):
+        """Test that PCRE supports lookbehind."""
+        pattern = r"(?<=pattern)"
+        unsupported = check_feature_support(pattern, "pcre")
+        assert "lookbehind" not in unsupported
+
 
 class TestCompatibilityWarnings:
+    """Tests for generating compatibility warnings."""
+
     def test_js_lookbehind_warning(self):
+        """Test warning for JavaScript lookbehind."""
         pattern = r"(?<=pattern)"
         warnings = get_compatibility_warnings(pattern, "javascript")
         assert len(warnings) > 0
@@ -70,12 +112,43 @@ class TestCompatibilityWarnings:
         assert "lookbehind" in warning_types
 
     def test_go_backreference_warning(self):
+        """Test warning for Go named backreferences."""
         pattern = r"\k<name>"
         warnings = get_compatibility_warnings(pattern, "go")
         warning_types = [w.feature for w in warnings]
-        assert "named_groups" in warning_types or "backreferences_general" in warning_types
+        assert "named_groups" in warning_types or "backreferences_general" in warning_types or "named_backreferences" in warning_types
 
     def test_pcre_no_warnings(self):
+        """Test that PCRE has no warnings for basic patterns."""
         pattern = r"\w+"
         warnings = get_compatibility_warnings(pattern, "pcre")
         assert len(warnings) == 0
+
+    def test_warning_severity(self):
+        """Test that warnings have proper severity levels."""
+        pattern = r"(?<=pattern)"
+        warnings = get_compatibility_warnings(pattern, "javascript")
+        assert len(warnings) > 0
+        for w in warnings:
+            assert w.severity in ("warning", "error")
+
+
+class TestFlavorAttributes:
+    """Tests for flavor attributes."""
+
+    def test_flavor_display_name(self):
+        """Test that flavors have display names."""
+        flavor = get_flavor("pcre")
+        assert flavor.display_name == "PCRE"
+        flavor = get_flavor("javascript")
+        assert flavor.display_name == "JavaScript"
+
+    def test_flavor_description(self):
+        """Test that flavors have descriptions."""
+        flavor = get_flavor("python")
+        assert len(flavor.description) > 0
+
+    def test_flavor_quirks(self):
+        """Test that flavors have quirk information."""
+        flavor = get_flavor("go")
+        assert len(flavor.quirks) > 0

tests/test_parser.py

@@ -12,18 +12,21 @@ from regex_humanizer.parser import (
     Group,
     Alternation,
     Anchor,
-    SpecialSequence,
 )
 
 
 class TestTokenizer:
+    """Tests for the tokenize function."""
+
     def test_tokenize_literal(self):
+        """Test tokenizing a literal string."""
         tokens = tokenize("abc")
         assert len(tokens) == 1
         assert tokens[0].type == "LITERAL"
         assert tokens[0].value == "abc"
 
     def test_tokenize_anchors(self):
+        """Test tokenizing anchor characters."""
         tokens = tokenize("^test$")
         assert len(tokens) == 3
         assert tokens[0].type == "ANCHOR_START"
@@ -31,18 +34,21 @@ class TestTokenizer:
         assert tokens[2].type == "ANCHOR_END"
 
     def test_tokenize_quantifiers(self):
+        """Test tokenizing quantifiers."""
         tokens = tokenize("a*")
         assert len(tokens) == 2
         assert tokens[0].type == "LITERAL"
         assert tokens[1].type == "STAR"
 
     def test_tokenize_character_class(self):
+        """Test tokenizing character classes."""
         tokens = tokenize("[abc]")
         assert len(tokens) >= 2
         assert tokens[0].type == "OPEN_BRACKET"
         assert tokens[-1].type == "CLOSE_BRACKET"
 
     def test_tokenize_groups(self):
+        """Test tokenizing groups."""
         tokens = tokenize("(abc)")
         assert len(tokens) == 3
         assert tokens[0].type == "OPEN_GROUP"
@@ -50,84 +56,117 @@ class TestTokenizer:
         assert tokens[2].type == "CLOSE_GROUP"
 
     def test_tokenize_alternation(self):
+        """Test tokenizing alternation."""
         tokens = tokenize("a|b")
         assert len(tokens) == 3
         assert tokens[0].type == "LITERAL"
         assert tokens[1].type == "ALTERNATION"
         assert tokens[2].type == "LITERAL"
 
+    def test_tokenize_escape(self):
+        """Test tokenizing escaped characters."""
+        tokens = tokenize(r"\.")
+        assert len(tokens) == 1
+        assert tokens[0].type == "ESCAPED"
+
+    def test_tokenize_special_sequences(self):
+        """Test tokenizing special sequences."""
+        tokens = tokenize(r"\d+\w*\s?")
+        assert len(tokens) >= 4
+
 
 class TestParser:
+    """Tests for the parse_regex function."""
+
     def test_parse_literal(self):
+        """Test parsing a literal pattern."""
         ast = parse_regex("hello")
         assert len(ast) == 1
         assert isinstance(ast[0], Literal)
         assert ast[0].value == "hello"
 
     def test_parse_character_class(self):
+        """Test parsing a character class."""
         ast = parse_regex("[abc]")
         assert len(ast) == 1
         assert isinstance(ast[0], CharacterClass)
 
     def test_parse_inverted_class(self):
+        """Test parsing an inverted class."""
         ast = parse_regex("[^abc]")
         assert len(ast) == 1
         assert isinstance(ast[0], CharacterClass)
         assert ast[0].inverted is True
 
     def test_parse_quantifier_star(self):
+        """Test parsing the * quantifier."""
         ast = parse_regex("a*")
         assert len(ast) == 1
         assert isinstance(ast[0], Quantifier)
 
     def test_parse_quantifier_plus(self):
+        """Test parsing the + quantifier."""
         ast = parse_regex("a+")
         assert len(ast) == 1
         assert isinstance(ast[0], Quantifier)
 
     def test_parse_quantifier_question(self):
+        """Test parsing the ? quantifier."""
         ast = parse_regex("a?")
         assert len(ast) == 1
         assert isinstance(ast[0], Quantifier)
 
     def test_parse_group(self):
+        """Test parsing a group."""
         ast = parse_regex("(abc)")
         assert len(ast) == 1
         assert isinstance(ast[0], Group)
         assert len(ast[0].content) == 1
+        assert isinstance(ast[0].content[0], Literal)
+        assert ast[0].content[0].value == "abc"
 
     def test_parse_non_capturing_group(self):
+        """Test parsing a non-capturing group."""
         ast = parse_regex("(?:abc)")
         assert len(ast) == 1
         assert isinstance(ast[0], Group)
         assert ast[0].capturing is False
 
     def test_parse_alternation(self):
+        """Test parsing alternation."""
         ast = parse_regex("a|b")
         assert len(ast) == 1
         assert isinstance(ast[0], Alternation)
         assert len(ast[0].options) == 2
 
     def test_parse_anchors(self):
+        """Test parsing anchors."""
         ast = parse_regex("^start$")
         assert len(ast) == 3
         assert isinstance(ast[0], Anchor)
+        assert isinstance(ast[1], Literal)
         assert isinstance(ast[2], Anchor)
+        assert ast[1].value == "start"
 
     def test_parse_special_sequences(self):
+        """Test parsing special sequences."""
         ast = parse_regex(r"\d+\w+")
         assert len(ast) == 2
         assert isinstance(ast[0], Quantifier)
+        assert isinstance(ast[1], Quantifier)
 
     def test_parse_complex_pattern(self):
+        """Test parsing a complex pattern."""
         pattern = r"^\w+@[a-z]+\.[a-z]+$"
         ast = parse_regex(pattern)
         assert len(ast) > 0
 
     def test_parse_error_unclosed_bracket(self):
+        """Test parsing error for unclosed bracket."""
         with pytest.raises(ParseError):
             parse_regex("[abc")
 
     def test_parse_error_unclosed_group(self):
+        """Test parsing error for unclosed group."""
         with pytest.raises(ParseError):
             parse_regex("(abc")