feat: support pre and post processing regex substitution (#15)

Also change to use more pydantic-settings instead of pyyaml.

.clog.yaml

@@ -42,3 +42,15 @@ breaking_changes_heading: BREAKING CHANGES 💥
 
 # Makes the Markdown bullet point neater with consistent capitalized first char
 capitalize_title_first_char: true
+
+# Pre and Post processing msg via regex to further amend the text
+# Preprocessing occurs before all other steps
+# Use Python Regex syntax for search and replace
+# preprocessing:
+#   search: '.+'
+#   replace: '\g<0>'
+
+# Postprocessing occurs after all other steps
+postprocessing:
+  search: '(.+)\(#(\d+)\)'
+  replace: '\1[#\2](https://github.com/dsaidgovsg/cc-changelog-gen/pull/\2)'

README.md

@@ -48,15 +48,11 @@ to auto-format the entire code base.
 The parsing of the commit messages (in particular the titles) can be controlled via the values set
 by `.clog.yaml` in the current working directory
 
-If you prefer to have a different file name or path to it, or even want to access it via http/https
-GET request, you can override this value:
+If you prefer to have a different file name or path to it, you can override this value, e.g.
 
-Example:
-
-- `-c /path/to/.clog.yaml`
-- `-c file:///path/to/.clog.yaml` (same effect as above)
-- `-c http://domain.com/.clog.yaml`
-- `-c https://domain.com/.clog.yaml`
+```bash
+cc-changelog-gen ... -c /path/to/.clog.yaml`
+```
 
 For the YAML specifications, as the parsing feature set is still growing and fairly unstable, there
 will not be any specifications yet and do expect new / breaking changes to take place (though any

pyproject.toml

@@ -15,7 +15,7 @@ authors = [
 ]
 dependencies = [
   "GitPython~=3.1.32",
-  "PyYAML~=6.0.1",
+  "pydantic-settings~=2.5.2",
   "semver~=3.0.1",
 ]
 

requirements.dev.txt

@@ -1,9 +1,11 @@
 #
-# This file is autogenerated by pip-compile with Python 3.10
+# This file is autogenerated by pip-compile with Python 3.11
 # by the following command:
 #
 #    pip-compile --extra=dev --output-file=requirements.dev.txt
 #
+annotated-types==0.7.0
+    # via pydantic
 black==23.7.0
     # via cc-changelog-gen (pyproject.toml)
 click==8.1.6
@@ -20,9 +22,19 @@ pathspec==0.11.2
     # via black
 platformdirs==3.10.0
     # via black
-pyyaml==6.0.1
+pydantic==2.9.2
+    # via pydantic-settings
+pydantic-core==2.23.4
+    # via pydantic
+pydantic-settings==2.5.2
+    # via cc-changelog-gen (pyproject.toml)
+python-dotenv==1.0.1
+    # via pydantic-settings
+semver==3.0.2
     # via cc-changelog-gen (pyproject.toml)
 smmap==5.0.0
     # via gitdb
-tomli==2.0.1
-    # via black
+typing-extensions==4.12.2
+    # via
+    #   pydantic
+    #   pydantic-core

requirements.txt

@@ -1,14 +1,28 @@
 #
-# This file is autogenerated by pip-compile with Python 3.10
+# This file is autogenerated by pip-compile with Python 3.11
 # by the following command:
 #
 #    pip-compile --output-file=requirements.txt
 #
+annotated-types==0.7.0
+    # via pydantic
 gitdb==4.0.10
     # via gitpython
 gitpython==3.1.32
     # via cc-changelog-gen (pyproject.toml)
-pyyaml==6.0.1
+pydantic==2.9.2
+    # via pydantic-settings
+pydantic-core==2.23.4
+    # via pydantic
+pydantic-settings==2.5.2
+    # via cc-changelog-gen (pyproject.toml)
+python-dotenv==1.0.1
+    # via pydantic-settings
+semver==3.0.2
     # via cc-changelog-gen (pyproject.toml)
 smmap==5.0.0
     # via gitdb
+typing-extensions==4.12.2
+    # via
+    #   pydantic
+    #   pydantic-core

src/cc_changelog_gen/app.py

@@ -1,16 +1,19 @@
 from argparse import ArgumentParser
 from collections import OrderedDict
 from dataclasses import dataclass, field
-from enum import Enum, auto
+from enum import Enum, StrEnum, auto
 from git import Repo, TagReference
-import os
+import os.path
+from pydantic import BaseModel
+from pydantic_settings import (
+    BaseSettings,
+    PydanticBaseSettingsSource,
+    YamlConfigSettingsSource,
+)
 import re
 import semver
 import sys
-from typing import Any, Dict, List, Optional
-from urllib.parse import urlparse
-import urllib.request
-import yaml
+from typing import Dict, List, Optional, Tuple, Type
 
 ALLOWED_SCHEME = ["file", "http", "https"]
 
@@ -23,7 +26,7 @@ def __str__(self) -> str:
         return f"Invalid scheme '{self.scheme}' to retrieve content from"
 
 
-class Color:
+class Color(StrEnum):
     WARNING = "\033[93m"
     ENDC = "\033[0m"
 
@@ -40,8 +43,12 @@ class Args:
     repo: str
 
 
-@dataclass
-class Conf:
+class Processing(BaseModel):
+    search: str
+    replace: str
+
+
+class Conf(BaseSettings):
     pre_captures: List[str] = field(default_factory=list)
     pre_captures_after_trim: str = r"\s+"
     type_captures: List[str] = field(default_factory=list)
@@ -56,6 +63,22 @@ class Conf:
     others_heading: str = "Others"
     breaking_changes_heading: str = "BREAKING CHANGES"
     capitalize_title_first_char: bool = True
+    preprocessing: Optional[Processing] = None
+    postprocessing: Optional[Processing] = None
+
+    @classmethod
+    def settings_customise_sources(
+        cls,
+        settings_cls: Type[BaseSettings],
+        init_settings: PydanticBaseSettingsSource,
+        env_settings: PydanticBaseSettingsSource,
+        dotenv_settings: PydanticBaseSettingsSource,
+        file_secret_settings: PydanticBaseSettingsSource,
+    ) -> Tuple[PydanticBaseSettingsSource, ...]:
+        # TODO: No better way to pass in runtime value until source changes:
+        # https://github.com/pydantic/pydantic-settings/issues/259
+        global YAML_FILE_PATH
+        return (YamlConfigSettingsSource(settings_cls, yaml_file=YAML_FILE_PATH),)
 
 
 class TypeMatch(Enum):
@@ -94,19 +117,6 @@ def get_values(self, heading: str) -> List[str]:
         return self.values[heading]
 
 
-def load_conf(conf_path: str) -> Dict[str, Any]:
-    conf_url = urlparse(conf_path)
-
-    if conf_url.scheme and conf_url.scheme not in ALLOWED_SCHEME:
-        raise ValueError("Protocol of given file is invalid")
-
-    if not conf_url.scheme:
-        conf_url = urlparse(f"file://{os.path.abspath(conf_path)}")
-
-    f = urllib.request.urlopen(conf_url.geturl()).read()
-    return yaml.safe_load(f)
-
-
 def args_parse() -> Args:
     parser = ArgumentParser(
         prog="Changelog Generator",
@@ -320,18 +330,20 @@ def process_breaking_change(
 
 def main():
     args = args_parse()
-    conf_dict = {}
 
     try:
-        conf_dict = load_conf(args.conf)
+        global YAML_FILE_PATH
+        YAML_FILE_PATH = args.conf
+        if not os.path.isfile(YAML_FILE_PATH):
+            raise FileNotFoundError(YAML_FILE_PATH)
     except OSError:
         print_color(
             Color.WARNING,
             f"Missing '{args.conf}' config file, using default values...",
             file=sys.stderr,
         )
 
-    c = Conf(**conf_dict)
+    c = Conf()
     repo = Repo(args.repo)
 
     # Commit parsing to find nearest previous semver tag
@@ -346,6 +358,9 @@ def main():
         messages = cm.message.split("\n")
         title = messages[0]
 
+        if c.preprocessing:
+            title = re.sub(c.preprocessing.search, c.preprocessing.replace, title)
+
         # Pre-capture logic
         title = process_pre_capture(
             title=title,
@@ -369,6 +384,9 @@ def main():
 
         title = type_capture_output.title
 
+        if c.postprocessing:
+            title = re.sub(c.postprocessing.search, c.postprocessing.replace, title)
+
         match type_capture_output.type_match:
             case TypeMatch.SUPPORTED_TYPE:
                 heading = c.supported_types[type_capture_output.type_capture]