whitespace-format 0.0.7__py3-none-any.whl → 0.0.8__py3-none-any.whl

{whitespace_format-0.0.7.dist-info → whitespace_format-0.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: whitespace-format
-Version: 0.0.7
+Version: 0.0.8
 Summary: Linter and formatter for source code files and text files
 License: MIT
 Author: David Pal
@@ -27,7 +27,7 @@ Description-Content-Type: text/markdown
 
 Linter and formatter for source code files and text files.
 
-The purpose of this tool is to normalize source code files (e.g. Python, Java,
+The purpose of this tool is to normalize source code files (e.g., Python, Java,
 C/C++, Ruby, Go, JavaScript, etc.) and text files (HTML, JSON, YAML, CSV,
 MarkDown, LaTeX) before checking them into a version control system.
 
@@ -94,7 +94,7 @@ The regular expression is evaluated on the path of each file.
 
 ### Formatting options
 
-* `--add-new-line-marker-at-end-of-file` -- Add missing new line marker at end of each file.
+* `--add-new-line-marker-at-end-of-file` -- Add missing new line marker at the end of each file.
 * `--remove-new-line-marker-from-end-of-file` -- Remove all new line marker(s) from the end of each file.
 This option cannot be used in combination with `--add-new-line-marker-at-end-of-file`.
 Empty lines at the end of the file are removed, i.e., this option implies `--remove-trailing-empty-lines`
@@ -112,7 +112,7 @@ adding or replacing new line markers. `MARKER` must be one of the following:
   * `mac` -- Use Mac new line marker `\r`.
   * `windows` -- Use Windows new line marker `\r\n`.
 * `--encoding` -- Text encoding for both reading and writing files. Default encoding is `utf-8`.
-List of supported encodings can be found at
+The list of supported encodings can be found at
 https://docs.python.org/3/library/codecs.html#standard-encodings
 
 Note that input files can contain an arbitrary mix of new line markers `\n`,
@@ -129,8 +129,8 @@ whitespace-format \
     --remove-trailing-empty-lines \
     foo.txt  my_project/
 ```
-This should work well for common programming languages (e.g. Python, Java,
-C/C++, JavaScript) and common text file formats (e.g. CSV, LaTeX, JSON, YAML,
+This should work well for common programming languages (e.g., Python, Java,
+C/C++, JavaScript) and common text file formats (e.g., CSV, LaTeX, JSON, YAML,
 HTML, MarkDown).
 
 ### Empty files
@@ -149,7 +149,7 @@ where `MODE` is one of the following:
 
 Depending on the mode, an empty file or a whitespace-only file will be either
 ignored, replaced by a zero-byte file, or replaced by a file consisting of
-single end of line marker.
+the single new line marker.
 
 If `--normalize-whitespace-only-files` is set to `empty`,
 `--normalize-empty-files setting` set to `empty` as well. In other words,
@@ -212,16 +212,17 @@ command `make delete-environment`.
 
 If you make code change, run unit tests and code checks with the command:
 ```shell
-make clean whitespace-format-check isort-check black-check flake8 pydocstyle pylint mypy test coverage
+make clean whitespace-format-check black-check isort-check pydocstyle ruff flake8 pylint mypy test coverage
 ```
 
 Each make target runs different checks:
 - `clean` deletes temporary files
 - `whitespace-format-check` runs [whitespace-format](https://github.com/DavidPal/whitespace-format) checker on all files
-- `isort-check` runs [isort](https://pycqa.github.io/isort/) checker of imports in `*.py` files
 - `black-check` runs [black](https://github.com/psf/black/) code format checker on `*.py` files
-- `flake8` runs [flake8](https://flake8.pycqa.org/) code style checker on `*.py` files
+- `isort-check` runs [isort](https://pycqa.github.io/isort/) checker of imports in `*.py` files
 - `pydocstyle` runs [pydocstyle](http://www.pydocstyle.org/) docstring checker on `*.py` files
+- `ruff` runs [ruff](https://docs.astral.sh/ruff/) code checker on `*.py` files
+- `flake8` runs [flake8](https://flake8.pycqa.org/) code style checker on `*.py` files
 - `pylint` runs [pylint](https://pylint.org/) code checker on `*.py` files
 - `mypy` runs [mypy](http://mypy-lang.org/) type checker on `*.py` files
 - `test` runs unit tests
@@ -229,7 +230,7 @@ Each make target runs different checks:
 
 You can automatically format code with the command:
 ```shell
-make isort-format black-format whitespace-format
+make whitespace-format isort-format black-format ruff-fix
 ```
 
 ## Modifying dependencies

whitespace_format-0.0.8.dist-info/RECORD

@@ -0,0 +1,6 @@
+whitespace_format.py,sha256=ClVXr7_0vrte2vk8KK7SC-GP8LldPcQMUkVLy-oqbAU,29302
+whitespace_format-0.0.8.dist-info/LICENSE,sha256=rT6UNfWDYFQc-eo65FioDJRMAyVOndtF95wNCUhkK74,1076
+whitespace_format-0.0.8.dist-info/METADATA,sha256=kzv3a9gkxqs2ik-3JYUrES3Rd2E3FDNBRi3DO1lvJ-Q,10517
+whitespace_format-0.0.8.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+whitespace_format-0.0.8.dist-info/entry_points.txt,sha256=LbXoevzUZAF5MVbI2foNC9xeDjKS_Woz7VbA1ZNF5CY,60
+whitespace_format-0.0.8.dist-info/RECORD,,

{whitespace_format-0.0.7.dist-info → whitespace_format-0.0.8.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.0.1
+Generator: poetry-core 2.1.3
 Root-Is-Purelib: true
 Tag: py3-none-any

whitespace_format.py

@@ -3,7 +3,7 @@
 """Formatter of whitespace in text files.
 
 Author: David Pal <davidko.pal@gmail.com>
-Date: 2023 - 2024
+Date: 2023 - 2025
 License: MIT License
 
 Usage:
@@ -22,7 +22,7 @@ from enum import Enum
 from typing import List
 from typing import Tuple
 
-VERSION = "0.0.7"
+VERSION = "0.0.8"
 
 # Regular expression that does NOT match any string.
 UNMATCHABLE_REGEX = "$."
@@ -83,23 +83,23 @@ ESCAPE_TRANSLATION_TABLE = str.maketrans(
         TAB: "\\t",
         VERTICAL_TAB: "\\v",
         FORM_FEED: "\\f",
-    }
+    },
 )
 
 
 class ChangeType(Enum):
     """Type of change that happened to a file."""
 
-    # New line marker was added to the end of the file (because it was missing).
+    # A new line marker was added to the end of the file (because it was missing).
     ADDED_NEW_LINE_MARKER_TO_END_OF_FILE = 1
 
-    # New line marker was removed from the end of the file.
+    # A new line marker was removed from the end of the file.
     REMOVED_NEW_LINE_MARKER_FROM_END_OF_FILE = 2
 
-    # New line marker was replaced by another one.
+    # A new line marker was replaced by another one.
     REPLACED_NEW_LINE_MARKER = 3
 
-    # White at the end of a line was removed.
+    # Whitespace at the end of a line was removed.
     REMOVED_TRAILING_WHITESPACE = 4
 
     # Empty line(s) at the end of file were removed.
@@ -114,7 +114,7 @@ class ChangeType(Enum):
     # A file consisting of only whitespace was replaced by a file consisting of single empty line.
     REPLACED_WHITESPACE_ONLY_FILE_WITH_ONE_LINE = 8
 
-    # A tab character was replaces by space character(s).
+    # A tab character was replaced by space character(s).
     REPLACED_TAB_WITH_SPACES = 9
 
     # A tab character was removed.
@@ -193,7 +193,7 @@ class Change:
         )
 
 
-def color_print(message: str, parsed_arguments: argparse.Namespace):
+def color_print(message: str, parsed_arguments: argparse.Namespace) -> None:
     """Outputs a colored message."""
     if parsed_arguments.quiet:
         return
@@ -218,7 +218,7 @@ def string_to_hex(text: str) -> str:
     return ":".join(f"{ord(character):02x}" for character in text)
 
 
-def die(error_code: int, message: str = ""):
+def die(error_code: int, message: str = "") -> None:
     """Exits the script."""
     if message:
         print(message)
@@ -240,7 +240,7 @@ def read_file_content(file_name: str, encoding: str) -> str:
     return ""
 
 
-def write_file(file_name: str, file_content: str, encoding: str):
+def write_file(file_name: str, file_content: str, encoding: str) -> None:
     """Writes data to a file."""
     try:
         with open(file_name, "w", encoding=encoding) as file:
@@ -251,10 +251,7 @@ def write_file(file_name: str, file_content: str, encoding: str):
 
 def is_whitespace_only(text: str) -> bool:
     """Determines if a string consists of only whitespace characters."""
-    for char in text:
-        if char not in WHITESPACE_CHARACTERS:
-            return False
-    return True
+    return all(char in WHITESPACE_CHARACTERS for char in text)
 
 
 def find_most_common_new_line_marker(text: str) -> str:
@@ -314,14 +311,14 @@ def format_file_content(
         find_most_common_new_line_marker(file_content),
     )
 
-    # Handle empty file:
+    # Handle an empty file.
     if not file_content:
         if parsed_arguments.normalize_empty_files in ["ignore", "empty"]:
             return "", []
         if parsed_arguments.normalize_empty_files == "one-line":
             return output_new_line_marker, [Change(ChangeType.REPLACED_EMPTY_FILE_WITH_ONE_LINE, 1)]
 
-    # Handle non-empty file consisting of whitespace only.
+    # Handle a non-empty file consisting of whitespace only.
     if is_whitespace_only(file_content):
         if parsed_arguments.normalize_whitespace_only_files == "empty":
             return "", [Change(ChangeType.REPLACED_WHITESPACE_ONLY_FILE_WITH_EMPTY_FILE, 1)]
@@ -329,7 +326,7 @@ def format_file_content(
             if file_content == output_new_line_marker:
                 return file_content, []
             return output_new_line_marker, [
-                Change(ChangeType.REPLACED_WHITESPACE_ONLY_FILE_WITH_ONE_LINE, 1)
+                Change(ChangeType.REPLACED_WHITESPACE_ONLY_FILE_WITH_ONE_LINE, 1),
             ]
         if parsed_arguments.normalize_whitespace_only_files == "ignore":
             return file_content, []
@@ -337,31 +334,31 @@ def format_file_content(
     # Index into the input buffer.
     i = 0
 
-    # List of changes
+    # List of changes.
     changes: List[Change] = []
 
     # Line number. It is incremented every time we encounter a new end of line marker.
     line_number = 1
 
-    # Position one character past the end of last line in the output buffer
+    # Index into the output buffer pointing just after the end of the last line,
     # including the last end of line marker.
     last_end_of_line_including_eol_marker = 0
 
-    # Position one character past the last non-whitespace character in the output buffer.
+    # Index into the output buffer pointing just after the last non-whitespace character.
     last_non_whitespace = 0
 
-    # Position one character past the end of last non-empty line in the output buffer
+    # Index into the output buffer pointing just after the end of the last non-empty line,
     # excluding the last end of line marker.
     last_end_of_non_empty_line_excluding_eol_marker = 0
 
-    # Position one character past the end of last non-empty line in the output buffer,
+    # Index into the output buffer pointing just after the end of the last non-empty line,
     # including the last end of line marker.
     last_end_of_non_empty_line_including_eol_marker = 0
 
     # Line number of the last non-empty line.
     last_non_empty_line_number = 0
 
-    # Formatted output
+    # Formatted output.
     output = ""
 
     while i < len(file_content):
@@ -378,31 +375,32 @@ def format_file_content(
             else:
                 new_line_marker = CARRIAGE_RETURN
 
-            # Remove trailing whitespace
-            if parsed_arguments.remove_trailing_whitespace and max(
-                last_non_whitespace, last_end_of_line_including_eol_marker
-            ) < len(output):
+            # Index into the output buffer pointing just after the last non-whitespace character
+            # on the current line. If the current line is empty, it is pointing to the beginning
+            # of the current line (i.e., just after the end of the previous line).
+            last_non_whitespace_on_current_line = max(
+                last_non_whitespace,
+                last_end_of_line_including_eol_marker,
+            )
+
+            # Remove trailing whitespace.
+            if (
+                parsed_arguments.remove_trailing_whitespace
+                and last_non_whitespace_on_current_line < len(output)
+            ):
                 changes.append(
-                    Change(
-                        ChangeType.REMOVED_TRAILING_WHITESPACE,
-                        line_number,
-                    )
+                    Change(ChangeType.REMOVED_TRAILING_WHITESPACE, line_number),
                 )
-                output = output[
-                    : max(
-                        last_non_whitespace,
-                        last_end_of_line_including_eol_marker,
-                    )
-                ]
-
-            # Determine if the last line is empty
+                output = output[:last_non_whitespace_on_current_line]
+
+            # Determine if the last line is empty.
             is_empty_line: bool = last_end_of_line_including_eol_marker == len(output)
 
-            # Position one character past the end of last line in the output buffer
+            # Index into the output buffer pointing just after the end of the last line,
             # excluding the last end of line marker.
             last_end_of_line_excluding_eol_marker = len(output)
 
-            # Add new line marker
+            # Add new line marker.
             if (
                 parsed_arguments.normalize_new_line_markers
                 and output_new_line_marker != new_line_marker
@@ -413,7 +411,7 @@ def format_file_content(
                         line_number,
                         new_line_marker,
                         output_new_line_marker,
-                    )
+                    ),
                 )
                 output += output_new_line_marker
             else:
@@ -457,13 +455,16 @@ def format_file_content(
                         line_number,
                         file_content[i],
                         SPACE,
-                    )
+                    ),
                 )
             elif parsed_arguments.normalize_non_standard_whitespace == "remove":
                 changes.append(
                     Change(
-                        ChangeType.REMOVED_NONSTANDARD_WHITESPACE, line_number, file_content[i], ""
-                    )
+                        ChangeType.REMOVED_NONSTANDARD_WHITESPACE,
+                        line_number,
+                        file_content[i],
+                        "",
+                    ),
                 )
             else:
                 raise ValueError("Unknown value of normalize_non_standard_whitespace")
@@ -471,7 +472,7 @@ def format_file_content(
             output += file_content[i]
             last_non_whitespace = len(output)
 
-        # Move to the next character
+        # Move to the next character.
         i += 1
 
     # Remove trailing whitespace from the last line.
@@ -494,7 +495,7 @@ def format_file_content(
         changes.append(Change(ChangeType.REMOVED_EMPTY_LINES, line_number))
         output = output[:last_end_of_non_empty_line_including_eol_marker]
 
-    # Add new line marker at the end of the file
+    # Add new line marker at the end of the file.
     if (
         parsed_arguments.add_new_line_marker_at_end_of_file
         and last_end_of_line_including_eol_marker < len(output)
@@ -504,7 +505,7 @@ def format_file_content(
         last_end_of_line_including_eol_marker = len(output)
         line_number += 1
 
-    # Remove new line marker(s) from the end of the file
+    # Remove new line marker(s) from the end of the file.
     if (
         parsed_arguments.remove_new_line_marker_from_end_of_file
         and last_end_of_line_including_eol_marker == len(output)
@@ -530,7 +531,7 @@ def reformat_file(file_name: str, parsed_arguments: argparse.Namespace) -> bool:
     file_content = read_file_content(file_name, parsed_arguments.encoding)
     formatted_file_content, file_changes = format_file_content(file_content, parsed_arguments)
     if parsed_arguments.verbose:
-        color_print(f"[WHITE]Processing file [BOLD]{file_name}[RESET_ALL]...", parsed_arguments)
+        color_print(f"[WHITE]Processing file [BOLD]{file_name}[RESET_ALL] ...", parsed_arguments)
     if parsed_arguments.check_only:
         if file_changes:
             color_print(
@@ -566,7 +567,7 @@ def reformat_file(file_name: str, parsed_arguments: argparse.Namespace) -> bool:
     return bool(file_changes)
 
 
-def reformat_files(file_names: List[str], parsed_arguments: argparse.Namespace):
+def reformat_files(file_names: List[str], parsed_arguments: argparse.Namespace) -> None:
     """Reformats multiple files."""
     color_print(f"Processing {len(file_names)} file(s)...", parsed_arguments)
     num_changed_files = 0
@@ -617,13 +618,14 @@ def find_files_to_process(file_names: List[str], parsed_arguments: argparse.Name
     """Finds files that need to be processed.
 
     The function excludes files that match the regular expression specified
-    by the --exclude command line option.
+    by the "--exclude" command line option.
     """
     return [
         expanded_file_name
         for file_name in file_names
         for expanded_file_name in find_all_files_recursively(
-            file_name, parsed_arguments.follow_symlinks
+            file_name,
+            parsed_arguments.follow_symlinks,
         )
         if not re.search(parsed_arguments.exclude, expanded_file_name)
     ]
@@ -649,7 +651,7 @@ def parse_command_line() -> argparse.Namespace:
         "--encoding",
         help=(
             "Text encoding for both reading and writing files. Default encoding is utf-8. "
-            "List of supported encodings can be found at "
+            "The list of supported encodings can be found at "
             "https://docs.python.org/3/library/codecs.html#standard-encodings"
         ),
         required=False,
@@ -759,7 +761,7 @@ def parse_command_line() -> argparse.Namespace:
     group2 = parser.add_mutually_exclusive_group()
     group2.add_argument(
         "--add-new-line-marker-at-end-of-file",
-        help="Add missing new line marker at end of each file.",
+        help="Add missing new line marker at the end of each file.",
         required=False,
         default=False,
         action="store_true",
@@ -828,7 +830,7 @@ def parse_command_line() -> argparse.Namespace:
     return parsed_arguments
 
 
-def main():
+def main() -> None:
     """Formats white space in text files."""
     parsed_arguments = parse_command_line()
     file_names = find_files_to_process(parsed_arguments.input_files, parsed_arguments)

whitespace_format-0.0.7.dist-info/RECORD

@@ -1,6 +0,0 @@
-whitespace_format.py,sha256=Jl5SqNgDhgG9GixsCtTk2bFwri3Ez6msa8Asrqe99os,28942
-whitespace_format-0.0.7.dist-info/LICENSE,sha256=rT6UNfWDYFQc-eo65FioDJRMAyVOndtF95wNCUhkK74,1076
-whitespace_format-0.0.7.dist-info/METADATA,sha256=n9Nta0jpn-EVz1gVaMNtU7SuyAN9eECs87N0l3FIcvw,10411
-whitespace_format-0.0.7.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
-whitespace_format-0.0.7.dist-info/entry_points.txt,sha256=LbXoevzUZAF5MVbI2foNC9xeDjKS_Woz7VbA1ZNF5CY,60
-whitespace_format-0.0.7.dist-info/RECORD,,