Merge pull request #45 from fleetingbytes/develop

close #42, #44

CHANGELOG.md

@@ -2,6 +2,18 @@
 
 <!-- towncrier release notes start -->
 
+## 0.9.4 (2024-11-10)
+
+
+### Bugfixes
+
+- add missing import statement in `html_decapsulator.py` [#42](https://github.com/fleetingbytes/rtfparse/issues/42)
+
+
+### Development Details
+
+- replace `black` and `isort` with `ruff` [#44](https://github.com/fleetingbytes/rtfparse/issues/44)
+
 ## 0.9.3 (2024-11-01)
 
 

pyproject.toml

@@ -67,14 +67,13 @@ no-cov = "cov --no-cov {args}"
 
 [tool.hatch.envs.style]
 dependencies = [
-    "black",
-    "isort",
+    "ruff",
 ]
 
 [tool.hatch.envs.style.scripts]
 fmt = [
-    "isort .",
-    "black .",
+    "ruff format",
+    "ruff check",
 ]
 
 [tool.hatch.envs.tc]
@@ -108,11 +107,87 @@ exclude_lines = [
   "if TYPE_CHECKING:",
 ]
 
-[tool.black]
-    line-length = 102
+[tool.ruff]
+# Exclude a variety of commonly ignored directories.
+exclude = [
+    ".bzr",
+    ".direnv",
+    ".eggs",
+    ".git",
+    ".git-rewrite",
+    ".hg",
+    ".ipynb_checkpoints",
+    ".mypy_cache",
+    ".nox",
+    ".pants.d",
+    ".pyenv",
+    ".pytest_cache",
+    ".pytype",
+    ".ruff_cache",
+    ".svn",
+    ".tox",
+    ".venv",
+    ".vscode",
+    "__pypackages__",
+    "_build",
+    "buck-out",
+    "build",
+    "dist",
+    "node_modules",
+    "site-packages",
+    "venv",
+]
+
+# Same as Black.
+line-length = 150
+indent-width = 4
+
+# Assume Python 3.10
+target-version = "py310"
+
+[tool.ruff.lint]
+# Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)  codes by default.
+# Unlike Flake8, Ruff doesn't enable pycodestyle warnings (`W`) or
+# McCabe complexity (`C901`) by default.
+select = ["E4", "E7", "E9", "F"]
+ignore = []
+
+# Allow fix for all enabled rules (when `--fix`) is provided.
+fixable = ["ALL"]
+unfixable = []
+
+# Allow unused variables when underscore-prefixed.
+dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+
+[tool.ruff.lint.pycodestyle]
+max-line-length = 150
+
+[tool.ruff.format]
+# Like Black, use double quotes for strings.
+quote-style = "double"
+
+# Like Black, indent with spaces, rather than tabs.
+indent-style = "space"
+
+# Like Black, respect magic trailing commas.
+skip-magic-trailing-comma = false
+
+# Like Black, automatically detect the appropriate line ending.
+line-ending = "auto"
+
+# Enable auto-formatting of code examples in docstrings. Markdown,
+# reStructuredText code/literal blocks and doctests are all supported.
+#
+# This is currently disabled by default, but it is planned for this
+# to be opt-out in the future.
+docstring-code-format = true
 
-[tool.isort]
-    line_length = 102
+# Set the line length limit used when formatting code snippets in
+# docstrings.
+#
+# This only has an effect when the `docstring-code-format` setting is
+# enabled.
+docstring-code-line-length = "dynamic"
 
 [tool.towncrier]
 name = "rtfparse"

src/rtfparse/__about__.py

@@ -1,4 +1,4 @@
 #!/usr/bin/env python
 
 
-__version__ = "0.9.3"
+__version__ = "0.9.4"

src/rtfparse/__init__.py

@@ -2,7 +2,8 @@
 
 
 # Towncrier needs version
-from rtfparse.__about__ import __version__
+# from rtfparse.__about__ import __version__
+__all__ = ["rtfparse.__about__.__version__"]
 
 if __name__ == "__main__":
     from rtfparse.cli import main

src/rtfparse/cli.py

@@ -24,14 +24,10 @@ def setup_logger(directory: Path) -> logging.Logger:
     """
     try:
         provide_dir(directory)
-        logger_config = logging_conf.create_dict_config(
-            directory, "rtfparse.debug.log", "rtfparse.info.log", "rtfparse.errors.log"
-        )
+        logger_config = logging_conf.create_dict_config(directory, "rtfparse.debug.log", "rtfparse.info.log", "rtfparse.errors.log")
     except FileExistsError:
-        logger.error(
-            f"Failed to create the directory `{str(directory)}` because it already exists as a file."
-        )
-        logger.error(f"Please create the directory `{str(directory)}`")
+        print(f"Failed to create the directory `{str(directory)}` because it already exists as a file.")
+        print(f"Please create the directory `{str(directory)}`")
     finally:
         logging.config.dictConfig(logger_config)
         logger = logging.getLogger(__name__)
@@ -46,49 +42,22 @@ def argument_parser() -> ArgumentParser:
     Creates an argument parser for command line arguments
     """
     parser = ArgumentParser(description="RTF parser", prog="rtfparse")
-    parser.add_argument(
-        "-v",
-        "--version",
-        action="version",
-        version=" ".join(("%(prog)s", __version__)),
-        help="print out rtfparse version and exit",
-    )
-    parser.add_argument(
-        "-r", "--rtf-file", action="store", metavar="PATH", type=Path, help="path to the rtf file"
-    )
-    parser.add_argument(
-        "-m",
-        "--msg-file",
-        action="store",
-        metavar="PATH",
-        type=Path,
-        help="Parse RTF from MS Outlook's .msg file",
-    )
-    parser.add_argument(
-        "-d", "--decapsulate-html", action="store_true", help="Decapsulate HTML from RTF"
-    )
-    parser.add_argument(
-        "-i", "--embed-img", action="store_true", help="Embed images from email to HTML"
-    )
-    parser.add_argument(
-        "-o", "--output-file", metavar="PATH", type=Path, help="path to the desired output file"
-    )
-    parser.add_argument(
-        "-a",
-        "--attachments-dir",
-        metavar="PATH",
-        type=Path,
-        help="path to directory where to save email attachments",
-    )
+    parser.add_argument("-v", "--version", action="version", version=" ".join(("%(prog)s", __version__)), help="print out rtfparse version and exit")
+    parser.add_argument("-r", "--rtf-file", action="store", metavar="PATH", type=Path, help="path to the rtf file")
+    parser.add_argument("-m", "--msg-file", action="store", metavar="PATH", type=Path, help="Parse RTF from MS Outlook's .msg file")
+    parser.add_argument("-d", "--decapsulate-html", action="store_true", help="Decapsulate HTML from RTF")
+    parser.add_argument("-i", "--embed-img", action="store_true", help="Embed images from email to HTML")
+    parser.add_argument("-o", "--output-file", metavar="PATH", type=Path, help="path to the desired output file")
+    parser.add_argument("-a", "--attachments-dir", metavar="PATH", type=Path, help="path to directory where to save email attachments")
     return parser
 
 
 def decapsulate(rp: Rtf_Parser, target_file: Path) -> None:
     renderer = HTML_Decapsulator()
     with open(target_file, mode="w", encoding="utf-8") as htmlfile:
-        logger.info(f"Rendering the encapsulated HTML")
+        logger.info("Rendering the encapsulated HTML")
         renderer.render(rp.parsed, htmlfile)
-        logger.info(f"Encapsulated HTML rendered")
+        logger.info("Encapsulated HTML rendered")
 
 
 def run(cli_args: Namespace) -> None:
@@ -101,9 +70,7 @@ def run(cli_args: Namespace) -> None:
         if cli_args.attachments_dir:
             provide_dir(cli_args.attachments_dir)
             for attachment in msg.attachments:
-                with open(
-                    cli_args.attachments_dir / f"{attachment.longFilename}", mode="wb"
-                ) as att_file:
+                with open(cli_args.attachments_dir / f"{attachment.longFilename}", mode="wb") as att_file:
                     att_file.write(attachment.data)
         decompressed_rtf = cr.decompress(msg.compressedRtf)
         with open(cli_args.msg_file.with_suffix(".rtf"), mode="wb") as email_rtf:
@@ -119,7 +86,7 @@ def main() -> None:
     """
     Entry point for any component start from the commmand line
     """
-    logger.debug(f"rtfparse started")
+    logger.debug("rtfparse started")
     parser = argument_parser()
     argcomplete.autocomplete(parser)
     cli_args = parser.parse_args()
@@ -128,4 +95,4 @@ def main() -> None:
         run(cli_args)
     except Exception as err:
         logger.exception(f"Uncaught exception {repr(err)} occurred.")
-    logger.debug(f"rtfparse ended")
+    logger.debug("rtfparse ended")

src/rtfparse/entities.py

@@ -3,7 +3,6 @@
 
 import io
 import logging
-import re
 
 # Own modules
 from rtfparse import re_patterns, utils
@@ -19,9 +18,7 @@
 GROUP_START = BACKSLASH + IGNORABLE
 MAX_CW_LETTERS = 32  # As specified in RTF Spec
 INTEGER_MAGNITUDE = 32  # As specified in RTF Spec
-PLAIN_TEXT = CONTROL_WORD = (
-    BACKSLASH + MAX_CW_LETTERS + MINUS + len(str((1 << INTEGER_MAGNITUDE) // 2)) + DELIMITER
-)
+PLAIN_TEXT = CONTROL_WORD = BACKSLASH + MAX_CW_LETTERS + MINUS + len(str((1 << INTEGER_MAGNITUDE) // 2)) + DELIMITER
 
 
 class Entity:
@@ -37,23 +34,23 @@ def probe(cls, pattern: re_patterns.Bytes_Regex, file: io.BufferedReader) -> Byt
             logger.debug(f"{probed = }")
             file.seek(original_position)
             logger.debug(f"Probe returned to position {file.tell()}")
-            if match := re_patterns.group_start.match(probed):
+            if re_patterns.group_start.match(probed):
                 result = Bytestring_Type.GROUP_START
-            elif match := re_patterns.group_end.match(probed):
+            elif re_patterns.group_end.match(probed):
                 result = Bytestring_Type.GROUP_END
-            elif match := re_patterns.control_word.match(probed):
+            elif re_patterns.control_word.match(probed):
                 result = Bytestring_Type.CONTROL_WORD
-            elif match := re_patterns.control_symbol.match(probed):
+            elif re_patterns.control_symbol.match(probed):
                 result = Bytestring_Type.CONTROL_SYMBOL
-            elif match := re_patterns.plain_text.match(probed):
+            elif re_patterns.plain_text.match(probed):
                 result = Bytestring_Type.PLAIN_TEXT
             else:
-                logger.debug(f"This does not match anything, it's probably a newline, moving on")
+                logger.debug("This does not match anything, it's probably a newline, moving on")
                 original_position += 1
                 file.seek(original_position)
                 logger.debug(f"Probe moved to position {file.tell()}")
                 if not probed:
-                    logger.debug(f"Reached unexpected end of file.")
+                    logger.debug("Reached unexpected end of file.")
                     result = Bytestring_Type.GROUP_END
                     break
                 continue
@@ -85,16 +82,14 @@ def __init__(self, encoding: str, file: io.BufferedReader) -> None:
                 logger.debug(f"Final {self.control_name = }")
             target_position = self.start_position + match.span()[1]
             if match.group("other"):
-                logger.debug(
-                    f"Delimiter is {match.group('other').decode(self.encoding)}, len: {len(match.group('delimiter'))}"
-                )
+                logger.debug(f"Delimiter is {match.group('other').decode(self.encoding)}, len: {len(match.group('delimiter'))}")
                 target_position -= len(match.group("delimiter"))
             file.seek(target_position)
             # handle \binN:
             if self.control_name == "bin":
                 self.bindata = file.read(utils.twos_complement(self.parameter, INTEGER_MAGNITUDE))
         else:
-            logger.warning(f"Missing Control Word")
+            logger.warning("Missing Control Word")
             file.seek(self.start_position)
 
     def __repr__(self) -> str:
@@ -112,9 +107,7 @@ def __init__(self, encoding: str, file: io.BufferedReader) -> None:
         if self.text == "'":
             self.char = file.read(SYMBOL).decode(self.encoding)
             self.text = bytes((int(self.char, base=16),)).decode(self.encoding)
-            logger.debug(
-                f"Encountered escaped ANSI character, read two more bytes: {self.char}, character: {self.text}"
-            )
+            logger.debug(f"Encountered escaped ANSI character, read two more bytes: {self.char}, character: {self.text}")
             if self.text in "\\{}":
                 file.seek(file.tell() - SYMBOL)
 
@@ -127,16 +120,14 @@ def __init__(self, encoding: str, file: io.BufferedReader) -> None:
         super().__init__()
         self.encoding = encoding
         self.text = ""
-        logger.debug(f"Constructing Plain_Text")
+        logger.debug("Constructing Plain_Text")
         while True:
             self.start_position = file.tell()
             read = file.read(PLAIN_TEXT)
-            logger.debug(
-                f"Read file from {self.start_position} to position {file.tell()}, read: {read}"
-            )
+            logger.debug(f"Read file from {self.start_position} to position {file.tell()}, read: {read}")
             # see if we have read all the plain text there is:
             if match := re_patterns.plain_text.match(read):
-                logger.debug(f"This matches the plain text pattern")
+                logger.debug("This matches the plain text pattern")
                 _text = match.group("text").decode(self.encoding)
                 logger.debug(f"{_text = }")
                 self.text = "".join((self.text, _text))
@@ -158,7 +149,7 @@ def __repr__(self) -> str:
 class Group(Entity):
     def __init__(self, encoding: str, file: io.BufferedReader) -> None:
         super().__init__()
-        logger.debug(f"Group.__init__")
+        logger.debug("Group.__init__")
         self.encoding = encoding
         self.known = False
         self.name = "unknown"
@@ -177,9 +168,7 @@ def __init__(self, encoding: str, file: io.BufferedReader) -> None:
                 file.seek(self.start_position + GROUP_START - IGNORABLE)
                 logger.debug(f"Returned to position {file.tell()}")
         else:
-            logger.warning(
-                utils.warn(f"Expected a group but found no group start. Creating unknown group")
-            )
+            logger.warning(utils.warn("Expected a group but found no group start. Creating unknown group"))
             file.seek(self.start_position)
         while True:
             probed = self.probe(re_patterns.probe, file)