$title

From 6e717a277be2893a8d7bafa6b3784cffaf81f17e Mon Sep 17 00:00:00 2001 From: jaseg Date: Sat, 31 Dec 2022 23:38:19 +0100 Subject: Prepare package for PyPI upload --- .gitignore | 6 +- html_diff.py | 742 --------------------------------------------------------- pyproject.toml | 25 ++ src/wsdiff.py | 742 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 770 insertions(+), 745 deletions(-) delete mode 100644 html_diff.py create mode 100644 pyproject.toml create mode 100644 src/wsdiff.py diff --git a/.gitignore b/.gitignore index 8049d93..bbf2dd5 100644 --- a/.gitignore +++ b/.gitignore @@ -1,3 +1,3 @@ -index.html -test/ -venv/ +build +dist +**/*.egg-info diff --git a/html_diff.py b/html_diff.py deleted file mode 100644 index 0cf9b5c..0000000 --- a/html_diff.py +++ /dev/null @@ -1,742 +0,0 @@ -# MIT License -# -# Copyright (c) 2016 Alex Goodman -# -# Permission is hereby granted, free of charge, to any person obtaining a copy of -# this software and associated documentation files (the "Software"), to deal in -# the Software without restriction, including without limitation the rights to -# use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies -# of the Software, and to permit persons to whom the Software is furnished to do -# so, subject to the following conditions: -# -# The above copyright notice and this permission notice shall be included in all -# copies or substantial portions of the Software. -# -# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, -# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE -# SOFTWARE. - -import io -import os -import string -import html -import textwrap -import sys -import difflib -import argparse -import webbrowser -from collections import defaultdict -from pathlib import Path -import re -from itertools import groupby, chain - -import pygments -from pygments.formatters import HtmlFormatter -from pygments.lexer import RegexLexer -from pygments.lexers import get_lexer_by_name, guess_lexer_for_filename, get_all_lexers, LEXERS -from pygments import token - - -HTML_TEMPLATE = r''' - - - - - $title - - - - - - - -

- Split view - -

Auto

Split view

- -

-$body -

- - -''' - -PYGMENTS_CSS = ''' -body .hll { background-color: #ffffcc } -body { background: #ffffff; } -body .c { color: #177500 } /* Comment */ -body .err { color: #000000 } /* Error */ -body .k { color: #A90D91 } /* Keyword */ -body .l { color: #1C01CE } /* Literal */ -body .n { color: #000000 } /* Name */ -body .o { color: #000000 } /* Operator */ -body .cm { color: #177500 } /* Comment.Multiline */ -body .cp { color: #633820 } /* Comment.Preproc */ -body .c1 { color: #177500 } /* Comment.Single */ -body .cs { color: #177500 } /* Comment.Special */ -body .kc { color: #A90D91 } /* Keyword.Constant */ -body .kd { color: #A90D91 } /* Keyword.Declaration */ -body .kn { color: #A90D91 } /* Keyword.Namespace */ -body .kp { color: #A90D91 } /* Keyword.Pseudo */ -body .kr { color: #A90D91 } /* Keyword.Reserved */ -body .kt { color: #A90D91 } /* Keyword.Type */ -body .ld { color: #1C01CE } /* Literal.Date */ -body .m { color: #1C01CE } /* Literal.Number */ -body .s { color: #C41A16 } /* Literal.String */ -body .na { color: #836C28 } /* Name.Attribute */ -body .nb { color: #A90D91 } /* Name.Builtin */ -body .nc { color: #3F6E75 } /* Name.Class */ -body .no { color: #000000 } /* Name.Constant */ -body .nd { color: #000000 } /* Name.Decorator */ -body .ni { color: #000000 } /* Name.Entity */ -body .ne { color: #000000 } /* Name.Exception */ -body .nf { color: #000000 } /* Name.Function */ -body .nl { color: #000000 } /* Name.Label */ -body .nn { color: #000000 } /* Name.Namespace */ -body .nx { color: #000000 } /* Name.Other */ -body .py { color: #000000 } /* Name.Property */ -body .nt { color: #000000 } /* Name.Tag */ -body .nv { color: #000000 } /* Name.Variable */ -body .ow { color: #000000 } /* Operator.Word */ -body .mb { color: #1C01CE } /* Literal.Number.Bin */ -body .mf { color: #1C01CE } /* Literal.Number.Float */ -body .mh { color: #1C01CE } /* Literal.Number.Hex */ -body .mi { color: #1C01CE } /* Literal.Number.Integer */ -body .mo { color: #1C01CE } /* Literal.Number.Oct */ -body .sb { color: #C41A16 } /* Literal.String.Backtick */ -body .sc { color: #2300CE } /* Literal.String.Char */ -body .sd { color: #C41A16 } /* Literal.String.Doc */ -body .s2 { color: #C41A16 } /* Literal.String.Double */ -body .se { color: #C41A16 } /* Literal.String.Escape */ -body .sh { color: #C41A16 } /* Literal.String.Heredoc */ -body .si { color: #C41A16 } /* Literal.String.Interpol */ -body .sx { color: #C41A16 } /* Literal.String.Other */ -body .sr { color: #C41A16 } /* Literal.String.Regex */ -body .s1 { color: #C41A16 } /* Literal.String.Single */ -body .ss { color: #C41A16 } /* Literal.String.Symbol */ -body .bp { color: #5B269A } /* Name.Builtin.Pseudo */ -body .vc { color: #000000 } /* Name.Variable.Class */ -body .vg { color: #000000 } /* Name.Variable.Global */ -body .vi { color: #000000 } /* Name.Variable.Instance */ -body .il { color: #1C01CE } /* Literal.Number.Integer.Long */ - -/* -These styles are used to highlight each diff line. -Note: for partial like highlight change to "display:block-inline" -*/ -span.left_diff_change { - background-color: #FFE5B5; - display: block -} -span.left_diff_add { - background-color: #eeeeee; - display: block -} -span.left_diff_del { - background-color: #ffdddd; - display: block -} -span.lineno_q { - display: block; -} -span.right_diff_change { - background-color: #FFE5B5; - display: block -} -span.right_diff_add { - background-color: #ddffdd; - display: block -} -span.right_diff_del { - background-color: #eeeeee; - display: block -} -span.clearbg { - background-color: transparent; -} -''' - -class SexprLexer(RegexLexer): - name = 'KiCad S-Expression' - aliases = ['sexp'] - filenames = ['*.kicad_mod', '*.kicad_sym'] - - tokens = { - 'root': [ - (r'\s+', token.Whitespace), - (r'[()]', token.Punctuation), - (r'([+-]?\d+\.\d+)(?=[)\s])', token.Number), - (r'(-?\d+)(?=[)\s])', token.Number), - (r'"((?:[^"]|\\")*)"(?=[)\s])', token.String), - (r'([^()"\s]+)(?=[)\s])', token.Name), - ] - } - -from pygments.formatter import Formatter -from pygments.token import STANDARD_TYPES - -from functools import lru_cache - -@lru_cache(maxsize=256) -def get_token_class(ttype): - while not (name := STANDARD_TYPES.get(ttype)): - if ttype is token.Token: - return 'n' - ttype = ttype.parent - return name - -def iter_token_lines(tokensource): - lineno = 1 - for ttype, value in tokensource: - left, newline, right = value.partition('\n') - while newline: - yield lineno, ttype, left - lineno += 1 - left, newline, right = right.partition('\n') - if left != '': - yield lineno, ttype, left - -class RecordFormatter(Formatter): - def __init__(self, side, diff): - self.side = side - if side == 'right': - diff = [(right, left, change) for left, right, change in diff] - self.diff = diff - - def format(self, tokensource, outfile): - diff = iter(self.diff) - self.lines = [] - for lineno, tokens in groupby(iter_token_lines(tokensource), key=lambda arg: arg[0]): - - for (lineno_ours, diff_ours), (lineno_theirs, _diff_theirs), change in diff: - if lineno_ours == lineno: - break - else: - self.lines.append(f'') - assert lineno_ours == lineno - - if not change: - change_class = '' - elif not lineno_ours or not lineno_theirs: - change_class = ' insert' - else: - change_class = ' change' - - line = f'{lineno}' - - parts = re.split(r'(\00.|\01|$)', diff_ours) - source_pos = 0 - diff_markers = [] - if lineno_theirs: # Do not highlight word changes if the whole line got added or removed. - for span, sep in zip(parts[0:-2:2], parts[1:-2:2]): - source_pos += len(span) - diff_markers.append((source_pos, sep)) - - diff_class = '' - source_pos = 0 - for _lineno, ttype, value in tokens: - css_class = get_token_class(ttype) - - while diff_markers: - next_marker_pos, next_marker_type = diff_markers[0] - if source_pos <= next_marker_pos < source_pos + len(value): - split_pos = next_marker_pos - source_pos - left, value = value[:split_pos], value[split_pos:] - line += f'{html.escape(left)}' - source_pos += len(left) - diff_class = ' word_change' if next_marker_type.startswith('\0') else '' - diff_markers = diff_markers[1:] - else: - break - line += f'{html.escape(value)}' - source_pos += len(value) - - if css_class is not None: - line += '' - - line += '' - self.lines.append(line) - - for _ours_empty, (lineno_theirs, _diff_theirs), change in diff: - self.lines.append(f'') - assert change and lineno_theirs - -def html_diff_content(old, new, lexer): - diff = list(difflib._mdiff(old.splitlines(), new.splitlines())) - - fmt_l = RecordFormatter('left', diff) - pygments.highlight(old, lexer, fmt_l) - - fmt_r = RecordFormatter('right', diff) - pygments.highlight(new, lexer, fmt_r) - - return '\n'.join(chain.from_iterable(zip(fmt_l.lines, fmt_r.lines))) - -def html_diff_block(old, new, filename, lexer): - code = html_diff_content(old, new, lexer) - return textwrap.dedent(f'''

‭{filename}

- {code} -

''') - - -if __name__ == "__main__": - description = "Given two source files or directories this application creates an html page that highlights the differences between the two." - - parser = argparse.ArgumentParser(description=description) - parser.add_argument('-b', '--open', action='store_true', help='Open output file in a browser') - parser.add_argument('-s', '--syntax-css', help='Path to custom Pygments CSS file for code syntax highlighting') - parser.add_argument('-l', '--lexer', help='Manually select pygments lexer (default: guess from filename, use -L to list available lexers.)') - parser.add_argument('-L', '--list-lexers', action='store_true', help='List available lexers for -l/--lexer') - parser.add_argument('-t', '--pagetitle', help='Override page title of output HTML file') - parser.add_argument('-o', '--output', default=sys.stdout, type=argparse.FileType('w'), help='Name of output file (default: stdout)') - parser.add_argument('--header', action='store_true', help='Only output HTML header with stylesheets and stuff, and no diff') - parser.add_argument('--content', action='store_true', help='Only output HTML content, without header') - parser.add_argument('old', nargs='?', help='source file or directory to compare ("before" file)') - parser.add_argument('new', nargs='?', help='source file or directory to compare ("after" file)') - args = parser.parse_args() - - if args.list_lexers: - for longname, aliases, filename_patterns, _mimetypes in get_all_lexers(): - print(f'{longname:<20} alias {"/".join(aliases)} for {", ".join(filename_patterns)}') - sys.exit(0) - - if args.pagetitle or (args.old and args.new): - pagetitle = args.pagetitle or f'diff: {args.old} / {args.new}' - else: - pagetitle = 'diff' - - if args.syntax_css: - syntax_css = Path(args.syntax_css).read_text() - else: - syntax_css = PYGMENTS_CSS - - if args.header: - print(string.Template(HTML_TEMPLATE).substitute( - title=pagetitle, - pygments_css=syntax_css, - body='$body'), file=args.output) - sys.exit(0) - - if not (args.old and args.new): - print('Error: The command line arguments "old" and "new" are required.', file=sys.stderr) - parser.print_usage() - sys.exit(2) - - if args.open and args.output == sys.stdout: - print('Error: --open requires --output to be given.', file=sys.stderr) - parser.print_usage() - sys.exit(2) - - old, new = Path(args.old), Path(args.new) - if not old.exists(): - print(f'Error: Path "{old}" does not exist.', file=sys.stderr) - sys.exit(1) - - if not new.exists(): - print(f'Error: Path "{new}" does not exist.', file=sys.stderr) - sys.exit(1) - - if old.is_file() != new.is_file(): - print(f'Error: You must give either two files, or two paths to compare, not a mix of both.', file=sys.stderr) - sys.exit(1) - - if old.is_file(): - found_files = {str(new): (old, new)} - else: - found_files = defaultdict(lambda: [None, None]) - for fn in old.glob('**/*'): - found_files[str(fn.relative_to(old))][0] = fn - for fn in new.glob('**/*'): - found_files[str(fn.relative_to(new))][1] = fn - - diff_blocks = [] - for suffix, (old, new) in sorted(found_files.items()): - old_text = '' if old is None else old.read_text() - new_text = '' if new is None else new.read_text() - - if args.lexer: - lexer = get_lexer_by_name(lexer) - else: - if new.suffix.lower() in ('.kicad_mod', '.kicad_mod', '.kicad_pcb', '.kicad_sch')\ - or new.name == 'sym_lib_table': - lexer = SexprLexer() - else: - try: - lexer = guess_lexer_for_filename(new, new_text) - except: - lexer = get_lexer_by_name('text') - - diff_blocks.append(html_diff_block(old_text, new_text, suffix, lexer)) - body = '\n'.join(diff_blocks) - - if args.content: - print(body, file=args.output) - else: - print(string.Template(HTML_TEMPLATE).substitute( - title=pagetitle, - pygments_css=syntax_css, - body=body), file=args.output) - - if args.open: - webbrowser.open('file://' + str(Path(args.output.name).absolute())) - diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 0000000..380cfc2 --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,25 @@ +[project] +name = "wsdiff" +version = "0.1.0" +authors = [{name="jaseg", email="code@jaseg.de"}] +description = "wsdiff is a tool that produces a syntax-highlighted, self-contained, static HTML file that will show a colored, syntax-highlighted diff of two files or folders without external dependencies or javascript." +requires-python = ">=3.7" +readme = "README.md" +classifiers = [ + "Programming Language :: Python :: 3", + "License :: OSI Approved :: MIT License", + "Operating System :: OS Independent", + ] +dependencies = ["pygments"] + +[project.urls] +"Source" = "https://git.jaseg.de/wsdiff.git" +"Bug Tracker" = "https://github.com/jaseg/wsdiff/issues" + +[project.scripts] +wsdiff = "wsdiff:cli" + +[build-system] +requires = ["setuptools>=61.0"] +build-backend = "setuptools.build_meta" + diff --git a/src/wsdiff.py b/src/wsdiff.py new file mode 100644 index 0000000..777c2a5 --- /dev/null +++ b/src/wsdiff.py @@ -0,0 +1,742 @@ +# MIT License +# +# Copyright (c) 2016 Alex Goodman +# +# Permission is hereby granted, free of charge, to any person obtaining a copy of +# this software and associated documentation files (the "Software"), to deal in +# the Software without restriction, including without limitation the rights to +# use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies +# of the Software, and to permit persons to whom the Software is furnished to do +# so, subject to the following conditions: +# +# The above copyright notice and this permission notice shall be included in all +# copies or substantial portions of the Software. +# +# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +# SOFTWARE. + +import io +import os +import string +import html +import textwrap +import sys +import difflib +import argparse +import webbrowser +from collections import defaultdict +from pathlib import Path +import re +from itertools import groupby, chain + +import pygments +from pygments.formatters import HtmlFormatter +from pygments.lexer import RegexLexer +from pygments.lexers import get_lexer_by_name, guess_lexer_for_filename, get_all_lexers, LEXERS +from pygments import token + + +HTML_TEMPLATE = r''' + + + + + $title + + + + + + + +

+ Split view + +

Auto

Split view

+ +

+$body +

+ + +''' + +PYGMENTS_CSS = ''' +body .hll { background-color: #ffffcc } +body { background: #ffffff; } +body .c { color: #177500 } /* Comment */ +body .err { color: #000000 } /* Error */ +body .k { color: #A90D91 } /* Keyword */ +body .l { color: #1C01CE } /* Literal */ +body .n { color: #000000 } /* Name */ +body .o { color: #000000 } /* Operator */ +body .cm { color: #177500 } /* Comment.Multiline */ +body .cp { color: #633820 } /* Comment.Preproc */ +body .c1 { color: #177500 } /* Comment.Single */ +body .cs { color: #177500 } /* Comment.Special */ +body .kc { color: #A90D91 } /* Keyword.Constant */ +body .kd { color: #A90D91 } /* Keyword.Declaration */ +body .kn { color: #A90D91 } /* Keyword.Namespace */ +body .kp { color: #A90D91 } /* Keyword.Pseudo */ +body .kr { color: #A90D91 } /* Keyword.Reserved */ +body .kt { color: #A90D91 } /* Keyword.Type */ +body .ld { color: #1C01CE } /* Literal.Date */ +body .m { color: #1C01CE } /* Literal.Number */ +body .s { color: #C41A16 } /* Literal.String */ +body .na { color: #836C28 } /* Name.Attribute */ +body .nb { color: #A90D91 } /* Name.Builtin */ +body .nc { color: #3F6E75 } /* Name.Class */ +body .no { color: #000000 } /* Name.Constant */ +body .nd { color: #000000 } /* Name.Decorator */ +body .ni { color: #000000 } /* Name.Entity */ +body .ne { color: #000000 } /* Name.Exception */ +body .nf { color: #000000 } /* Name.Function */ +body .nl { color: #000000 } /* Name.Label */ +body .nn { color: #000000 } /* Name.Namespace */ +body .nx { color: #000000 } /* Name.Other */ +body .py { color: #000000 } /* Name.Property */ +body .nt { color: #000000 } /* Name.Tag */ +body .nv { color: #000000 } /* Name.Variable */ +body .ow { color: #000000 } /* Operator.Word */ +body .mb { color: #1C01CE } /* Literal.Number.Bin */ +body .mf { color: #1C01CE } /* Literal.Number.Float */ +body .mh { color: #1C01CE } /* Literal.Number.Hex */ +body .mi { color: #1C01CE } /* Literal.Number.Integer */ +body .mo { color: #1C01CE } /* Literal.Number.Oct */ +body .sb { color: #C41A16 } /* Literal.String.Backtick */ +body .sc { color: #2300CE } /* Literal.String.Char */ +body .sd { color: #C41A16 } /* Literal.String.Doc */ +body .s2 { color: #C41A16 } /* Literal.String.Double */ +body .se { color: #C41A16 } /* Literal.String.Escape */ +body .sh { color: #C41A16 } /* Literal.String.Heredoc */ +body .si { color: #C41A16 } /* Literal.String.Interpol */ +body .sx { color: #C41A16 } /* Literal.String.Other */ +body .sr { color: #C41A16 } /* Literal.String.Regex */ +body .s1 { color: #C41A16 } /* Literal.String.Single */ +body .ss { color: #C41A16 } /* Literal.String.Symbol */ +body .bp { color: #5B269A } /* Name.Builtin.Pseudo */ +body .vc { color: #000000 } /* Name.Variable.Class */ +body .vg { color: #000000 } /* Name.Variable.Global */ +body .vi { color: #000000 } /* Name.Variable.Instance */ +body .il { color: #1C01CE } /* Literal.Number.Integer.Long */ + +/* +These styles are used to highlight each diff line. +Note: for partial like highlight change to "display:block-inline" +*/ +span.left_diff_change { + background-color: #FFE5B5; + display: block +} +span.left_diff_add { + background-color: #eeeeee; + display: block +} +span.left_diff_del { + background-color: #ffdddd; + display: block +} +span.lineno_q { + display: block; +} +span.right_diff_change { + background-color: #FFE5B5; + display: block +} +span.right_diff_add { + background-color: #ddffdd; + display: block +} +span.right_diff_del { + background-color: #eeeeee; + display: block +} +span.clearbg { + background-color: transparent; +} +''' + +class SexprLexer(RegexLexer): + name = 'KiCad S-Expression' + aliases = ['sexp'] + filenames = ['*.kicad_mod', '*.kicad_sym'] + + tokens = { + 'root': [ + (r'\s+', token.Whitespace), + (r'[()]', token.Punctuation), + (r'([+-]?\d+\.\d+)(?=[)\s])', token.Number), + (r'(-?\d+)(?=[)\s])', token.Number), + (r'"((?:[^"]|\\")*)"(?=[)\s])', token.String), + (r'([^()"\s]+)(?=[)\s])', token.Name), + ] + } + +from pygments.formatter import Formatter +from pygments.token import STANDARD_TYPES + +from functools import lru_cache + +@lru_cache(maxsize=256) +def get_token_class(ttype): + while not (name := STANDARD_TYPES.get(ttype)): + if ttype is token.Token: + return 'n' + ttype = ttype.parent + return name + +def iter_token_lines(tokensource): + lineno = 1 + for ttype, value in tokensource: + left, newline, right = value.partition('\n') + while newline: + yield lineno, ttype, left + lineno += 1 + left, newline, right = right.partition('\n') + if left != '': + yield lineno, ttype, left + +class RecordFormatter(Formatter): + def __init__(self, side, diff): + self.side = side + if side == 'right': + diff = [(right, left, change) for left, right, change in diff] + self.diff = diff + + def format(self, tokensource, outfile): + diff = iter(self.diff) + self.lines = [] + for lineno, tokens in groupby(iter_token_lines(tokensource), key=lambda arg: arg[0]): + + for (lineno_ours, diff_ours), (lineno_theirs, _diff_theirs), change in diff: + if lineno_ours == lineno: + break + else: + self.lines.append(f'') + assert lineno_ours == lineno + + if not change: + change_class = '' + elif not lineno_ours or not lineno_theirs: + change_class = ' insert' + else: + change_class = ' change' + + line = f'{lineno}' + + parts = re.split(r'(\00.|\01|$)', diff_ours) + source_pos = 0 + diff_markers = [] + if lineno_theirs: # Do not highlight word changes if the whole line got added or removed. + for span, sep in zip(parts[0:-2:2], parts[1:-2:2]): + source_pos += len(span) + diff_markers.append((source_pos, sep)) + + diff_class = '' + source_pos = 0 + for _lineno, ttype, value in tokens: + css_class = get_token_class(ttype) + + while diff_markers: + next_marker_pos, next_marker_type = diff_markers[0] + if source_pos <= next_marker_pos < source_pos + len(value): + split_pos = next_marker_pos - source_pos + left, value = value[:split_pos], value[split_pos:] + line += f'{html.escape(left)}' + source_pos += len(left) + diff_class = ' word_change' if next_marker_type.startswith('\0') else '' + diff_markers = diff_markers[1:] + else: + break + line += f'{html.escape(value)}' + source_pos += len(value) + + if css_class is not None: + line += '' + + line += '' + self.lines.append(line) + + for _ours_empty, (lineno_theirs, _diff_theirs), change in diff: + self.lines.append(f'') + assert change and lineno_theirs + +def html_diff_content(old, new, lexer): + diff = list(difflib._mdiff(old.splitlines(), new.splitlines())) + + fmt_l = RecordFormatter('left', diff) + pygments.highlight(old, lexer, fmt_l) + + fmt_r = RecordFormatter('right', diff) + pygments.highlight(new, lexer, fmt_r) + + return '\n'.join(chain.from_iterable(zip(fmt_l.lines, fmt_r.lines))) + +def html_diff_block(old, new, filename, lexer): + code = html_diff_content(old, new, lexer) + return textwrap.dedent(f'''

‭{filename}

+ {code} +

''') + + +def cli(): + parser = argparse.ArgumentParser(description="Given two source files or directories this application creates an html page that highlights the differences between the two.") + parser.add_argument('-b', '--open', action='store_true', help='Open output file in a browser') + parser.add_argument('-s', '--syntax-css', help='Path to custom Pygments CSS file for code syntax highlighting') + parser.add_argument('-l', '--lexer', help='Manually select pygments lexer (default: guess from filename, use -L to list available lexers.)') + parser.add_argument('-L', '--list-lexers', action='store_true', help='List available lexers for -l/--lexer') + parser.add_argument('-t', '--pagetitle', help='Override page title of output HTML file') + parser.add_argument('-o', '--output', default=sys.stdout, type=argparse.FileType('w'), help='Name of output file (default: stdout)') + parser.add_argument('--header', action='store_true', help='Only output HTML header with stylesheets and stuff, and no diff') + parser.add_argument('--content', action='store_true', help='Only output HTML content, without header') + parser.add_argument('old', nargs='?', help='source file or directory to compare ("before" file)') + parser.add_argument('new', nargs='?', help='source file or directory to compare ("after" file)') + args = parser.parse_args() + + if args.list_lexers: + for longname, aliases, filename_patterns, _mimetypes in get_all_lexers(): + print(f'{longname:<20} alias {"/".join(aliases)} for {", ".join(filename_patterns)}') + sys.exit(0) + + if args.pagetitle or (args.old and args.new): + pagetitle = args.pagetitle or f'diff: {args.old} / {args.new}' + else: + pagetitle = 'diff' + + if args.syntax_css: + syntax_css = Path(args.syntax_css).read_text() + else: + syntax_css = PYGMENTS_CSS + + if args.header: + print(string.Template(HTML_TEMPLATE).substitute( + title=pagetitle, + pygments_css=syntax_css, + body='$body'), file=args.output) + sys.exit(0) + + if not (args.old and args.new): + print('Error: The command line arguments "old" and "new" are required.', file=sys.stderr) + parser.print_usage() + sys.exit(2) + + if args.open and args.output == sys.stdout: + print('Error: --open requires --output to be given.', file=sys.stderr) + parser.print_usage() + sys.exit(2) + + old, new = Path(args.old), Path(args.new) + if not old.exists(): + print(f'Error: Path "{old}" does not exist.', file=sys.stderr) + sys.exit(1) + + if not new.exists(): + print(f'Error: Path "{new}" does not exist.', file=sys.stderr) + sys.exit(1) + + if old.is_file() != new.is_file(): + print(f'Error: You must give either two files, or two paths to compare, not a mix of both.', file=sys.stderr) + sys.exit(1) + + if old.is_file(): + found_files = {str(new): (old, new)} + else: + found_files = defaultdict(lambda: [None, None]) + for fn in old.glob('**/*'): + found_files[str(fn.relative_to(old))][0] = fn + for fn in new.glob('**/*'): + found_files[str(fn.relative_to(new))][1] = fn + + diff_blocks = [] + for suffix, (old, new) in sorted(found_files.items()): + old_text = '' if old is None else old.read_text() + new_text = '' if new is None else new.read_text() + + if args.lexer: + lexer = get_lexer_by_name(lexer) + else: + if new.suffix.lower() in ('.kicad_mod', '.kicad_mod', '.kicad_pcb', '.kicad_sch')\ + or new.name == 'sym_lib_table': + lexer = SexprLexer() + else: + try: + lexer = guess_lexer_for_filename(new, new_text) + except: + lexer = get_lexer_by_name('text') + + diff_blocks.append(html_diff_block(old_text, new_text, suffix, lexer)) + body = '\n'.join(diff_blocks) + + if args.content: + print(body, file=args.output) + else: + print(string.Template(HTML_TEMPLATE).substitute( + title=pagetitle, + pygments_css=syntax_css, + body=body), file=args.output) + + if args.open: + webbrowser.open('file://' + str(Path(args.output.name).absolute())) + +if __name__ == "__main__": + cli() -- cgit