feat(unicode): add unicode support

This will allow commiting, e.g., emoji's and parsing commit messages for
unicode characters when creating change logs.

Author: adam-grant-hendry

commitizen/bump.py

@@ -8,7 +8,7 @@
 from commitizen.defaults import MAJOR, MINOR, PATCH, bump_message
 from commitizen.exceptions import CurrentVersionNotFoundError
 from commitizen.git import GitCommit, smart_open
-from commitizen.version_schemes import DEFAULT_SCHEME, VersionScheme, Version
+from commitizen.version_schemes import DEFAULT_SCHEME, Version, VersionScheme
 
 
 def find_increment(
@@ -45,7 +45,12 @@ def find_increment(
 
 
 def update_version_in_files(
-    current_version: str, new_version: str, files: list[str], *, check_consistency=False
+    current_version: str,
+    new_version: str,
+    files: List[str],
+    encoding: str,
+    *,
+    check_consistency=False,
 ) -> None:
     """Change old version to the new one in every file given.
 
@@ -62,7 +67,11 @@ def update_version_in_files(
             regex = _version_to_regex(current_version)
 
         current_version_found, version_file = _bump_with_regex(
-            filepath, current_version, new_version, regex
+            filepath,
+            current_version,
+            new_version,
+            regex,
+            encoding,
         )
 
         if check_consistency and not current_version_found:
@@ -73,17 +82,21 @@ def update_version_in_files(
             )
 
         # Write the file out again
-        with smart_open(filepath, "w") as file:
+        with smart_open(filepath, "w", encoding=encoding) as file:
             file.write(version_file)
 
 
 def _bump_with_regex(
-    version_filepath: str, current_version: str, new_version: str, regex: str
-) -> tuple[bool, str]:
+    version_filepath: str,
+    current_version: str,
+    new_version: str,
+    regex: str,
+    encoding: str,
+) -> Tuple[bool, str]:
     current_version_found = False
     lines = []
     pattern = re.compile(regex)
-    with open(version_filepath, "r") as f:
+    with open(version_filepath, "r", encoding=encoding) as f:
         for line in f:
             if pattern.search(line):
                 bumped_line = line.replace(current_version, new_version)

commitizen/changelog.py

@@ -227,7 +227,7 @@ def get_metadata(filepath: str, scheme: VersionScheme = Pep440) -> dict:
             "latest_version_position": None,
         }
 
-    with open(filepath, "r") as changelog_file:
+    with open(filepath, "r", encoding=encoding) as changelog_file:
         for index, line in enumerate(changelog_file):
             line = line.strip().lower()
 

commitizen/changelog_parser.py

@@ -36,7 +36,7 @@
 ]
 
 
-def find_version_blocks(filepath: str) -> Generator:
+def find_version_blocks(filepath: str, encoding: str) -> Generator:
     """Find version block (version block: contains all the information about a version.)
 
     E.g:
@@ -53,7 +53,7 @@ def find_version_blocks(filepath: str) -> Generator:
 
     ```
     """
-    with open(filepath, "r") as f:
+    with open(filepath, "r", encoding=encoding) as f:
         block: list = []
         for line in f:
             line = line.strip("\n")

commitizen/commands/bump.py

@@ -36,6 +36,7 @@ def __init__(self, config: BaseConfig, arguments: dict):
             raise NotAGitProjectError()
 
         self.config: BaseConfig = config
+        self.encoding = config.settings["encoding"]
         self.arguments: dict = arguments
         self.bump_settings: dict = {
             **config.settings,
@@ -297,6 +298,7 @@ def __call__(self):  # noqa: C901
             str(current_version),
             str(new_version),
             version_files,
+            self.encoding,
             check_consistency=self.check_consistency,
         )
 

commitizen/commands/changelog.py

@@ -27,6 +27,7 @@ def __init__(self, config: BaseConfig, args):
             raise NotAGitProjectError()
 
         self.config: BaseConfig = config
+        self.encoding = self.config.settings["encoding"]
         self.cz = factory.commiter_factory(self.config)
 
         self.start_rev = args.get("start_rev") or self.config.settings.get(
@@ -100,9 +101,9 @@ def write_changelog(
                 f"or the setting `changelog_file` in {self.config.path}"
             )
 
-        changelog_hook: Callable | None = self.cz.changelog_hook
-        with smart_open(self.file_name, "w") as changelog_file:
-            partial_changelog: str | None = None
+        changelog_hook: Optional[Callable] = self.cz.changelog_hook
+        with smart_open(self.file_name, "w", encoding=self.encoding) as changelog_file:
+            partial_changelog: Optional[str] = None
             if self.incremental:
                 new_lines = changelog.incremental_build(
                     changelog_out, lines, changelog_meta
@@ -141,7 +142,9 @@ def __call__(self):
 
         end_rev = ""
         if self.incremental:
-            changelog_meta = changelog.get_metadata(self.file_name, self.scheme)
+            changelog_meta = changelog.get_metadata(
+                self.file_name, self.scheme, self.encoding
+            )
             latest_version = changelog_meta.get("latest_version")
             if latest_version:
                 latest_tag_version: str = bump.normalize_tag(
@@ -187,7 +190,7 @@ def __call__(self):
 
         lines = []
         if self.incremental and os.path.isfile(self.file_name):
-            with open(self.file_name, "r") as changelog_file:
+            with open(self.file_name, "r", encoding=self.encoding) as changelog_file:
                 lines = changelog_file.readlines()
 
         self.write_changelog(changelog_out, lines, changelog_meta)

commitizen/commands/check.py

@@ -44,6 +44,7 @@ def __init__(self, config: BaseConfig, arguments: dict[str, Any], cwd=os.getcwd(
         self._valid_command_argument()
 
         self.config: BaseConfig = config
+        self.encoding = config.settings["encoding"]
         self.cz = factory.commiter_factory(self.config)
 
     def _valid_command_argument(self):
@@ -97,7 +98,7 @@ def _get_commits(self):
         # Get commit message from file (--commit-msg-file)
         if self.commit_msg_file is not None:
             # Enter this branch if commit_msg_file is "".
-            with open(self.commit_msg_file, "r", encoding="utf-8") as commit_file:
+            with open(self.commit_msg_file, "r", encoding=self.encoding) as commit_file:
                 msg = commit_file.read()
         # Get commit message from command line (--message)
         elif self.commit_msg is not None:

commitizen/commands/commit.py

@@ -28,6 +28,7 @@ def __init__(self, config: BaseConfig, arguments: dict):
             raise NotAGitProjectError()
 
         self.config: BaseConfig = config
+        self.encoding = config.settings["encoding"]
         self.cz = factory.commiter_factory(self.config)
         self.arguments = arguments
         self.temp_file: str = os.path.join(
@@ -41,7 +42,7 @@ def read_backup_message(self) -> str:
             raise NoCommitBackupError()
 
         # Read commit message from backup
-        with open(self.temp_file, "r") as f:
+        with open(self.temp_file, "r", encoding=self.encoding) as f:
             return f.read().strip()
 
     def prompt_commit_questions(self) -> str:
@@ -99,7 +100,7 @@ def __call__(self):
             out.error(c.err)
 
             # Create commit backup
-            with smart_open(self.temp_file, "w") as f:
+            with smart_open(self.temp_file, "w", encoding=self.encoding) as f:
                 f.write(m)
 
             raise CommitError()

commitizen/commands/init.py

@@ -72,6 +72,7 @@ def is_pre_commit_installed(self) -> bool:
 class Init:
     def __init__(self, config: BaseConfig, *args):
         self.config: BaseConfig = config
+        self.encoding = config.settings["encoding"]
         self.cz = factory.commiter_factory(self.config)
         self.project_info = ProjectInfo()
 
@@ -324,7 +325,9 @@ def _install_pre_commit_hook(self, hook_types: list[str] | None = None):
             # .pre-commit-config.yaml does not exist
             config_data["repos"] = [cz_hook_config]
         else:
-            with open(pre_commit_config_filename) as config_file:
+            with open(
+                pre_commit_config_filename, encoding=self.encoding
+            ) as config_file:
                 yaml_data = yaml.safe_load(config_file)
                 if yaml_data:
                     config_data = yaml_data
@@ -340,7 +343,9 @@ def _install_pre_commit_hook(self, hook_types: list[str] | None = None):
                 # .pre-commit-config.yaml exists but there's no "repos" key
                 config_data["repos"] = [cz_hook_config]
 
-        with smart_open(pre_commit_config_filename, "w") as config_file:
+        with smart_open(
+            pre_commit_config_filename, "w", encoding=self.encoding
+        ) as config_file:
             yaml.safe_dump(config_data, stream=config_file)
 
         if not self.project_info.is_pre_commit_installed:

commitizen/config/json_config.py

@@ -12,12 +12,13 @@
 class JsonConfig(BaseConfig):
     def __init__(self, *, data: bytes | str, path: Path | str):
         super(JsonConfig, self).__init__()
+        self.encoding = self.settings["encoding"]
         self.is_empty_config = False
         self.add_path(path)
         self._parse_setting(data)
 
     def init_empty_config_content(self):
-        with smart_open(self.path, "a") as json_file:
+        with smart_open(self.path, "a", encoding=self.encoding) as json_file:
             json.dump({"commitizen": {}}, json_file)
 
     def set_key(self, key, value):
@@ -30,7 +31,7 @@ def set_key(self, key, value):
             parser = json.load(f)
 
         parser["commitizen"][key] = value
-        with smart_open(self.path, "w") as f:
+        with smart_open(self.path, "w", encoding=self.encoding) as f:
             json.dump(parser, f, indent=2)
         return self
 

commitizen/config/toml_config.py

@@ -11,6 +11,7 @@
 class TomlConfig(BaseConfig):
     def __init__(self, *, data: bytes | str, path: Path | str):
         super(TomlConfig, self).__init__()
+        self.encoding = self.settings["encoding"]
         self.is_empty_config = False
         self._parse_setting(data)
         self.add_path(path)
@@ -26,7 +27,7 @@ def init_empty_config_content(self):
             if parser.get("tool") is None:
                 parser["tool"] = table()
             parser["tool"]["commitizen"] = table()
-            output_toml_file.write(parser.as_string().encode("utf-8"))
+            output_toml_file.write(parser.as_string().encode(self.encoding))
 
     def set_key(self, key, value):
         """Set or update a key in the conf.
@@ -39,7 +40,7 @@ def set_key(self, key, value):
 
         parser["tool"]["commitizen"][key] = value
         with open(self.path, "wb") as f:
-            f.write(parser.as_string().encode("utf-8"))
+            f.write(parser.as_string().encode(self.encoding))
         return self
 
     def _parse_setting(self, data: bytes | str) -> None:

commitizen/config/yaml_config.py

@@ -12,12 +12,13 @@
 class YAMLConfig(BaseConfig):
     def __init__(self, *, data: bytes | str, path: Path | str):
         super(YAMLConfig, self).__init__()
+        self.encoding = self.settings["encoding"]
         self.is_empty_config = False
         self._parse_setting(data)
         self.add_path(path)
 
     def init_empty_config_content(self):
-        with smart_open(self.path, "a") as json_file:
+        with smart_open(self.path, "a", encoding=self.encoding) as json_file:
             yaml.dump({"commitizen": {}}, json_file, explicit_start=True)
 
     def _parse_setting(self, data: bytes | str) -> None:
@@ -44,7 +45,7 @@ def set_key(self, key, value):
             parser = yaml.load(yaml_file, Loader=yaml.FullLoader)
 
         parser["commitizen"][key] = value
-        with smart_open(self.path, "w") as yaml_file:
+        with smart_open(self.path, "w", encoding=self.encoding) as yaml_file:
             yaml.dump(parser, yaml_file, explicit_start=True)
 
         return self

commitizen/cz/conventional_commits/conventional_commits.py

@@ -202,7 +202,7 @@ def schema_pattern(self) -> str:
     def info(self) -> str:
         dir_path = os.path.dirname(os.path.realpath(__file__))
         filepath = os.path.join(dir_path, "conventional_commits_info.txt")
-        with open(filepath, "r") as f:
+        with open(filepath, "r", encoding=self.config.settings["encoding"]) as f:
             content = f.read()
         return content
 

commitizen/cz/customize/customize.py

@@ -81,7 +81,7 @@ def info(self) -> str | None:
         info_path = self.custom_settings.get("info_path")
         info = self.custom_settings.get("info")
         if info_path:
-            with open(info_path, "r") as f:
+            with open(info_path, "r", encoding=self.config.settings["encoding"]) as f:
                 content = f.read()
             return content
         elif info:

commitizen/cz/jira/jira.py

@@ -76,6 +76,6 @@ def schema_pattern(self) -> str:
     def info(self) -> str:
         dir_path = os.path.dirname(os.path.realpath(__file__))
         filepath = os.path.join(dir_path, "jira_info.txt")
-        with open(filepath, "r") as f:
+        with open(filepath, "r", encoding=self.config.settings["encoding"]) as f:
             content = f.read()
         return content

commitizen/defaults.py

@@ -55,6 +55,7 @@ class Settings(TypedDict, total=False):
     pre_bump_hooks: list[str] | None
     post_bump_hooks: list[str] | None
     prerelease_offset: int
+    encoding: str
 
 
 name: str = "cz_conventional_commits"
@@ -66,6 +67,7 @@ class Settings(TypedDict, total=False):
     ".cz.yaml",
     "cz.yaml",
 ]
+encoding: str = "utf-8"
 
 DEFAULT_SETTINGS: Settings = {
     "name": "cz_conventional_commits",
@@ -93,6 +95,7 @@ class Settings(TypedDict, total=False):
     "pre_bump_hooks": [],
     "post_bump_hooks": [],
     "prerelease_offset": 0,
+    "encoding": "utf-8",
 }
 
 MAJOR = "MAJOR"