flowmark 0.4.2__tar.gz → 0.4.4__tar.gz

{flowmark-0.4.2 → flowmark-0.4.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: flowmark
-Version: 0.4.2
+Version: 0.4.4
 Summary: Better line wrapping and formatting for plaintext and Markdown
 Project-URL: Repository, https://github.com/jlevy/flowmark
 Author-email: Joshua Levy <joshua@cal.berkeley.edu>
@@ -153,7 +153,9 @@ experience.
 Flowmark can be used as a library or as a CLI.
 
 ```
-usage: flowmark [-h] [-o OUTPUT] [-w WIDTH] [-p] [-s] [-i] [--nobackup] [--auto] [--version] [file]
+usage: flowmark [-h] [-o OUTPUT] [-w WIDTH] [-p] [-s] [-c] [-i] [--nobackup] [--auto]
+                [--version]
+                [file]
 
 Flowmark: Better line wrapping and formatting for plaintext and Markdown
 
@@ -165,10 +167,14 @@ options:
   -o, --output OUTPUT  Output file (use '-' for stdout)
   -w, --width WIDTH    Line width to wrap to
   -p, --plaintext      Process as plaintext (no Markdown parsing)
-  -s, --semantic       Enable semantic (sentence-based) line breaks (only applies to Markdown mode)
+  -s, --semantic       Enable semantic (sentence-based) line breaks (only applies to
+                       Markdown mode)
+  -c, --cleanups       Enable (safe) cleanups for common issues like accidentally
+                       boldfaced section headers (only applies to Markdown mode)
   -i, --inplace        Edit the file in place (ignores --output)
   --nobackup           Do not make a backup of the original file when using --inplace
-  --auto               Same as `--inplace --nobackup --semantic`, as a convenience for auto-formatting files
+  --auto               Same as `--inplace --nobackup --semantic --cleanups`, as a
+                       convenience for fully auto-formatting files
   --version            Show version information and exit
 
 Flowmark provides enhanced text wrapping capabilities with special handling for

{flowmark-0.4.2 → flowmark-0.4.4}/README.md

@@ -129,7 +129,9 @@ experience.
 Flowmark can be used as a library or as a CLI.
 
 ```
-usage: flowmark [-h] [-o OUTPUT] [-w WIDTH] [-p] [-s] [-i] [--nobackup] [--auto] [--version] [file]
+usage: flowmark [-h] [-o OUTPUT] [-w WIDTH] [-p] [-s] [-c] [-i] [--nobackup] [--auto]
+                [--version]
+                [file]
 
 Flowmark: Better line wrapping and formatting for plaintext and Markdown
 
@@ -141,10 +143,14 @@ options:
   -o, --output OUTPUT  Output file (use '-' for stdout)
   -w, --width WIDTH    Line width to wrap to
   -p, --plaintext      Process as plaintext (no Markdown parsing)
-  -s, --semantic       Enable semantic (sentence-based) line breaks (only applies to Markdown mode)
+  -s, --semantic       Enable semantic (sentence-based) line breaks (only applies to
+                       Markdown mode)
+  -c, --cleanups       Enable (safe) cleanups for common issues like accidentally
+                       boldfaced section headers (only applies to Markdown mode)
   -i, --inplace        Edit the file in place (ignores --output)
   --nobackup           Do not make a backup of the original file when using --inplace
-  --auto               Same as `--inplace --nobackup --semantic`, as a convenience for auto-formatting files
+  --auto               Same as `--inplace --nobackup --semantic --cleanups`, as a
+                       convenience for fully auto-formatting files
   --version            Show version information and exit
 
 Flowmark provides enhanced text wrapping capabilities with special handling for

{flowmark-0.4.2 → flowmark-0.4.4}/src/flowmark/__init__.py

@@ -6,6 +6,8 @@ __all__ = (
     "html_md_word_splitter",
     "line_wrap_by_sentence",
     "line_wrap_to_width",
+    "reformat_file",
+    "reformat_text",
     "split_sentences_regex",
     "wrap_paragraph",
     "wrap_paragraph_lines",
@@ -14,6 +16,7 @@ __all__ = (
 
 from .line_wrappers import line_wrap_by_sentence, line_wrap_to_width
 from .markdown_filling import fill_markdown
+from .reformat_api import reformat_file, reformat_text
 from .sentence_split_regex import first_sentence, first_sentences, split_sentences_regex
 from .text_filling import Wrap, fill_text
 from .text_wrapping import html_md_word_splitter, wrap_paragraph, wrap_paragraph_lines

{flowmark-0.4.2 → flowmark-0.4.4}/src/flowmark/cli.py

@@ -41,9 +41,7 @@ import importlib.metadata
 import sys
 from dataclasses import dataclass
 
-from strif import atomic_output_file
-
-from flowmark import Wrap, fill_markdown, fill_text, html_md_word_splitter
+from flowmark.reformat_api import reformat_file
 
 
 @dataclass
@@ -104,7 +102,8 @@ def _parse_args(args: list[str] | None = None) -> Options:
         "--cleanups",
         action="store_true",
         default=False,
-        help="Enable (safe) cleanups for common issues (only applies to Markdown mode)",
+        help="Enable (safe) cleanups for common issues like accidentally boldfaced section "
+        "headers (only applies to Markdown mode)",
     )
     parser.add_argument(
         "-i", "--inplace", action="store_true", help="Edit the file in place (ignores --output)"
@@ -117,7 +116,8 @@ def _parse_args(args: list[str] | None = None) -> Options:
     parser.add_argument(
         "--auto",
         action="store_true",
-        help="Same as `--inplace --nobackup --semantic`, as a convenience for auto-formatting files",
+        help="Same as `--inplace --nobackup --semantic --cleanups`, as a convenience for "
+        "fully auto-formatting files",
     )
     parser.add_argument(
         "--version",
@@ -130,6 +130,7 @@ def _parse_args(args: list[str] | None = None) -> Options:
         opts.inplace = True
         opts.nobackup = True
         opts.semantic = True
+        opts.cleanups = True
 
     return Options(
         file=opts.file,
@@ -165,46 +166,26 @@ def main(args: list[str] | None = None) -> int:
             print("unknown (package not installed)")
         return 0
 
-    # Handle input.
-    if options.file == "-":
-        text = sys.stdin.read()
-    else:
-        with open(options.file) as f:
-            text = f.read()
-
-    if options.plaintext:
-        # Plaintext mode
-        result = fill_text(
-            text,
-            text_wrap=Wrap.WRAP,
-            width=options.width,
-            word_splitter=html_md_word_splitter,  # Still use HTML/MD aware splitter by default
-        )
-    else:
-        # Markdown mode
-        result = fill_markdown(
-            text,
+    try:
+        reformat_file(
+            path=options.file,
+            output=options.output,
             width=options.width,
+            inplace=options.inplace,
+            nobackup=options.nobackup,
+            plaintext=options.plaintext,
             semantic=options.semantic,
             cleanups=options.cleanups,
-            dedent_input=True,
+            make_parents=True,
         )
-
-    # Handle output
-    if options.inplace:
-        if options.file == "-":
-            print("Error: Cannot use --inplace with stdin", file=sys.stderr)
-            return 1
-        backup_suffix = ".orig" if not options.nobackup else ""
-        with atomic_output_file(options.file, backup_suffix=backup_suffix) as tmp_path:
-            with open(tmp_path, "w") as f:
-                f.write(result)
-    else:
-        if options.output == "-":
-            sys.stdout.write(result)
-        else:
-            with open(options.output, "w") as f:
-                f.write(result)
+    except ValueError as e:
+        # Handle errors reported by reformat_file, like using --inplace with stdin.
+        print(f"Error: {e}", file=sys.stderr)
+        return 1
+    except Exception as e:
+        # Catch other potential file or processing errors.
+        print(f"Error: {e}", file=sys.stderr)
+        return 2
 
     return 0
 

flowmark-0.4.4/src/flowmark/reformat_api.py

@@ -0,0 +1,91 @@
+import sys
+from pathlib import Path
+
+from strif import atomic_output_file
+
+from flowmark.markdown_filling import fill_markdown
+from flowmark.text_filling import Wrap, fill_text
+from flowmark.text_wrapping import html_md_word_splitter
+
+
+def reformat_text(
+    text: str,
+    width: int = 88,
+    plaintext: bool = False,
+    semantic: bool = True,
+    cleanups: bool = True,
+) -> str:
+    """
+    Reformat text or markdown and wrap lines. Simply a convenient wrapper
+    around `fill_text()` and `fill_markdown()` with reasonable defaults.
+    """
+    if plaintext:
+        # Plaintext mode
+        result = fill_text(
+            text,
+            text_wrap=Wrap.WRAP,
+            width=width,
+            word_splitter=html_md_word_splitter,  # Still use HTML/MD aware splitter by default
+        )
+    else:
+        # Markdown mode
+        result = fill_markdown(text, width=width, semantic=semantic, cleanups=cleanups)
+
+    return result
+
+
+def reformat_file(
+    path: Path | str,
+    output: Path | str | None,
+    width: int = 88,
+    inplace: bool = False,
+    nobackup: bool = False,
+    plaintext: bool = False,
+    semantic: bool = False,
+    cleanups: bool = True,
+    make_parents: bool = True,
+) -> None:
+    """
+    Reformat text or markdown and wrap lines on the given files.
+    Accepts "-" for stdin. Can omit output if `inplace` is True.
+    Throws usual file-related exceptions if the input or output is invalid.
+
+    Args:
+        path: Path to the input file, or "-" for stdin.
+        output: Path to the output file, or "-" for stdout.
+        width: The width to wrap lines to.
+        inplace: Whether to write the file back to the same path (atomically only on success).
+        nobackup: Whether to not make a backup of the original file
+        plaintext: Use plaintext instead of Markdown mode wrapping.
+        semantic: Use semantic line breaks (based on sentences) heuristic.
+        cleanups: Enable (safe) cleanups for common issues like accidentally boldfaced section
+            headers (only applies to Markdown mode).
+        make_parents: Whether to make parent directories if they don't exist.
+    """
+    read_stdin = path == "-"
+    write_stdout = output == "-"
+
+    if inplace and read_stdin:
+        raise ValueError("Cannot use `inplace` with stdin")
+    if inplace and output and output != path:
+        raise ValueError("Cannot use `inplace` with an output path")
+
+    if read_stdin:
+        text = sys.stdin.read()
+    else:
+        text = Path(path).read_text()
+
+    result = reformat_text(text, width, plaintext, semantic, cleanups)
+
+    if inplace:
+        backup_suffix = ".orig" if not nobackup else ""
+        with atomic_output_file(
+            path, backup_suffix=backup_suffix, make_parents=make_parents
+        ) as tmp_path:
+            tmp_path.write_text(result)
+    else:
+        if not output or write_stdout:
+            sys.stdout.write(result)
+        else:
+            with atomic_output_file(output, make_parents=make_parents) as tmp_path:
+                tmp_path.write_text(result)

{flowmark-0.4.2 → flowmark-0.4.4}/src/flowmark/text_wrapping.py

@@ -74,7 +74,7 @@ Split words, but not within HTML tags or Markdown links.
 # Pattern to identify words that need escaping if they start a wrapped markdown line.
 # Matches list markers (*, +, -) bare or before a space (but not before a letter for
 # example), blockquotes (> ), headings (#, ##, etc.).
-_md_specials_pat = re.compile(r"^[-*+](?: |$)|> |#+$")
+_md_specials_pat = re.compile(r"^([-*+>]|#+)$")
 
 # Separate pattern to specifically find the numbered list cases for targeted escaping
 _md_numeral_pat = re.compile(r"^[0-9]+[.)]$")

{flowmark-0.4.2 → flowmark-0.4.4}/tests/test_wrapping.py

@@ -15,7 +15,7 @@ def test_markdown_escape_word_function() -> None:
     assert markdown_escape_word("-") == "\\-"
     assert markdown_escape_word("+") == "\\+"
     assert markdown_escape_word("*") == "\\*"
-    assert markdown_escape_word(">") == ">"
+    assert markdown_escape_word(">") == "\\>"
     assert markdown_escape_word("#") == "\\#"
     assert markdown_escape_word("##") == "\\##"
     assert markdown_escape_word("1.") == "1\\."
@@ -52,7 +52,7 @@ def test_wrap_paragraph_lines_markdown_escaping():
         "word",
         "\\+",
         "word",
-        ">",
+        "\\>",
         "word",
         "\\#",
         "word",

{flowmark-0.4.2 → flowmark-0.4.4}/tests/testdocs/testdoc.orig.md

@@ -546,6 +546,8 @@ And people often put them before punctuation like this[^a], or this[^a]. Or even
 
 ❗️️️ Having multiple automatic conversion thresholds can give the investor with a higher threshold leverage to block an IPO.[^210]
 
+1. **Initial Scan with -X importtime:** Run the application with python -X importtime... > import.log. Visualize the output using tuna import.log.<sup>42</sup> Look for modules with large *cumulative* times at the top level or deep in the call stack. These are the primary candidates for further investigation.<sup>1</sup>
+
 [^2]: Aulet, Bill. *Disciplined Entrepreneurship*: 24 Steps to a Successful Startup (Kindle Location 1220). Wiley, 2013. Kindle Edition.
 
 [^191]: http://paulgraham.com/fr.html

{flowmark-0.4.2 → flowmark-0.4.4}/tests/testdocs/testdoc.out.cleaned.md

@@ -867,6 +867,11 @@ not complaining)[^urbanthowt.wy49lp].
 ❗️️️ Having multiple automatic conversion thresholds can give the investor with a higher
 threshold leverage to block an IPO.[^210]
 
+1. **Initial Scan with -X importtime:** Run the application with python -X importtime...
+   \> import.log. Visualize the output using tuna import.log.<sup>42</sup> Look for
+   modules with large *cumulative* times at the top level or deep in the call stack.
+   These are the primary candidates for further investigation.<sup>1</sup>
+
 [^2]: Aulet, Bill. *Disciplined Entrepreneurship*: 24 Steps to a Successful Startup (Kindle
     Location 1220). Wiley, 2013. Kindle Edition.
 

{flowmark-0.4.2 → flowmark-0.4.4}/tests/testdocs/testdoc.out.plain.md

@@ -829,6 +829,11 @@ not complaining)[^urbanthowt.wy49lp].
 ❗️️️ Having multiple automatic conversion thresholds can give the investor with a higher
 threshold leverage to block an IPO.[^210]
 
+1. **Initial Scan with -X importtime:** Run the application with python -X importtime...
+   \> import.log. Visualize the output using tuna import.log.<sup>42</sup> Look for
+   modules with large *cumulative* times at the top level or deep in the call stack.
+   These are the primary candidates for further investigation.<sup>1</sup>
+
 [^2]: Aulet, Bill. *Disciplined Entrepreneurship*: 24 Steps to a Successful Startup
     (Kindle Location 1220). Wiley, 2013. Kindle Edition.
 

{flowmark-0.4.2 → flowmark-0.4.4}/tests/testdocs/testdoc.out.semantic.md

@@ -867,6 +867,11 @@ not complaining)[^urbanthowt.wy49lp].
 ❗️️️ Having multiple automatic conversion thresholds can give the investor with a higher
 threshold leverage to block an IPO.[^210]
 
+1. **Initial Scan with -X importtime:** Run the application with python -X importtime...
+   \> import.log. Visualize the output using tuna import.log.<sup>42</sup> Look for
+   modules with large *cumulative* times at the top level or deep in the call stack.
+   These are the primary candidates for further investigation.<sup>1</sup>
+
 [^2]: Aulet, Bill. *Disciplined Entrepreneurship*: 24 Steps to a Successful Startup (Kindle
     Location 1220). Wiley, 2013. Kindle Edition.