From 237ae081dbade817f4a2033b6aa2d3cdeb15b8b2 Mon Sep 17 00:00:00 2001 From: Sébastien Dailly Date: Sat, 15 Nov 2014 21:22:30 +0100 Subject: Moved typogrify as plugin --- plugins/typogrify/titlecase/__init__.py | 101 ++++++++++++++++++ plugins/typogrify/titlecase/tests.py | 174 ++++++++++++++++++++++++++++++++ 2 files changed, 275 insertions(+) create mode 100755 plugins/typogrify/titlecase/__init__.py create mode 100644 plugins/typogrify/titlecase/tests.py (limited to 'plugins/typogrify/titlecase') diff --git a/plugins/typogrify/titlecase/__init__.py b/plugins/typogrify/titlecase/__init__.py new file mode 100755 index 0000000..aeaca97 --- /dev/null +++ b/plugins/typogrify/titlecase/__init__.py @@ -0,0 +1,101 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +# titlecase v0.5.1 +# Copyright (C) 2008-2010, Stuart Colville. +# https://pypi.python.org/pypi/titlecase + +""" +Original Perl version by: John Gruber http://daringfireball.net/ 10 May 2008 +Python version by Stuart Colville http://muffinresearch.co.uk +License: http://www.opensource.org/licenses/mit-license.php +""" + +import re + +__all__ = ['titlecase'] +__version__ = '0.5.1' + +SMALL = 'a|an|and|as|at|but|by|en|for|if|in|of|on|or|the|to|v\.?|via|vs\.?' +PUNCT = r"""!"#$%&'‘()*+,\-./:;?@[\\\]_`{|}~""" + +SMALL_WORDS = re.compile(r'^(%s)$' % SMALL, re.I) +INLINE_PERIOD = re.compile(r'[a-z][.][a-z]', re.I) +UC_ELSEWHERE = re.compile(r'[%s]*?[a-zA-Z]+[A-Z]+?' % PUNCT) +CAPFIRST = re.compile(r"^[%s]*?([A-Za-z])" % PUNCT) +SMALL_FIRST = re.compile(r'^([%s]*)(%s)\b' % (PUNCT, SMALL), re.I) +SMALL_LAST = re.compile(r'\b(%s)[%s]?$' % (SMALL, PUNCT), re.I) +SUBPHRASE = re.compile(r'([:.;?!][ ])(%s)' % SMALL) +APOS_SECOND = re.compile(r"^[dol]{1}['‘]{1}[a-z]+$", re.I) +ALL_CAPS = re.compile(r'^[A-Z\s%s]+$' % PUNCT) +UC_INITIALS = re.compile(r"^(?:[A-Z]{1}\.{1}|[A-Z]{1}\.{1}[A-Z]{1})+$") +MAC_MC = re.compile(r"^([Mm]a?c)(\w+)") + +def titlecase(text): + + """ + Titlecases input text + + This filter changes all words to Title Caps, and attempts to be clever + about *un*capitalizing SMALL words like a/an/the in the input. + + The list of "SMALL words" which are not capped comes from + the New York Times Manual of Style, plus 'vs' and 'v'. + + """ + + lines = re.split('[\r\n]+', text) + processed = [] + for line in lines: + all_caps = ALL_CAPS.match(line) + words = re.split('[\t ]', line) + tc_line = [] + for word in words: + if all_caps: + if UC_INITIALS.match(word): + tc_line.append(word) + continue + else: + word = word.lower() + + if APOS_SECOND.match(word): + word = word.replace(word[0], word[0].upper()) + word = word.replace(word[2], word[2].upper()) + tc_line.append(word) + continue + if INLINE_PERIOD.search(word) or UC_ELSEWHERE.match(word): + tc_line.append(word) + continue + if SMALL_WORDS.match(word): + tc_line.append(word.lower()) + continue + + match = MAC_MC.match(word) + if match: + tc_line.append("%s%s" % (match.group(1).capitalize(), + match.group(2).capitalize())) + continue + + hyphenated = [] + for item in word.split('-'): + hyphenated.append(CAPFIRST.sub(lambda m: m.group(0).upper(), item)) + tc_line.append("-".join(hyphenated)) + + + result = " ".join(tc_line) + + result = SMALL_FIRST.sub(lambda m: '%s%s' % ( + m.group(1), + m.group(2).capitalize() + ), result) + + result = SMALL_LAST.sub(lambda m: m.group(0).capitalize(), result) + + result = SUBPHRASE.sub(lambda m: '%s%s' % ( + m.group(1), + m.group(2).capitalize() + ), result) + + processed.append(result) + + return "\n".join(processed) + diff --git a/plugins/typogrify/titlecase/tests.py b/plugins/typogrify/titlecase/tests.py new file mode 100644 index 0000000..97a45e4 --- /dev/null +++ b/plugins/typogrify/titlecase/tests.py @@ -0,0 +1,174 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- + +"""Tests for titlecase""" + + +import os +import sys +sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../')) + +from titlecase import titlecase + +TEST_DATA = ( + ( + "Q&A with steve jobs: 'that's what happens in technology'", + "Q&A With Steve Jobs: 'That's What Happens in Technology'" + ), + ( + "What is AT&T's problem?", + "What Is AT&T's Problem?" + ), + ( + "Apple deal with AT&T falls through", + "Apple Deal With AT&T Falls Through" + ), + ( + "this v that", + "This v That" + ), + ( + "this v. that", + "This v. That" + ), + ( + "this vs that", + "This vs That" + ), + ( + "this vs. that", + "This vs. That" + ), + ( + "The SEC's Apple probe: what you need to know", + "The SEC's Apple Probe: What You Need to Know" + ), + ( + "'by the Way, small word at the start but within quotes.'", + "'By the Way, Small Word at the Start but Within Quotes.'" + ), + ( + "Small word at end is nothing to be afraid of", + "Small Word at End Is Nothing to Be Afraid Of" + ), + ( + "Starting Sub-Phrase With a Small Word: a Trick, Perhaps?", + "Starting Sub-Phrase With a Small Word: A Trick, Perhaps?" + ), + ( + "Sub-Phrase With a Small Word in Quotes: 'a Trick, Perhaps?'", + "Sub-Phrase With a Small Word in Quotes: 'A Trick, Perhaps?'" + ), + ( + 'sub-phrase with a small word in quotes: "a trick, perhaps?"', + 'Sub-Phrase With a Small Word in Quotes: "A Trick, Perhaps?"' + ), + ( + '"Nothing to Be Afraid of?"', + '"Nothing to Be Afraid Of?"' + ), + ( + '"Nothing to be Afraid Of?"', + '"Nothing to Be Afraid Of?"' + ), + ( + 'a thing', + 'A Thing' + ), + ( + "2lmc Spool: 'gruber on OmniFocus and vapo(u)rware'", + "2lmc Spool: 'Gruber on OmniFocus and Vapo(u)rware'" + ), + ( + 'this is just an example.com', + 'This Is Just an example.com' + ), + ( + 'this is something listed on del.icio.us', + 'This Is Something Listed on del.icio.us' + ), + ( + 'iTunes should be unmolested', + 'iTunes Should Be Unmolested' + ), + ( + 'reading between the lines of steve jobs’s ‘thoughts on music’', + 'Reading Between the Lines of Steve Jobs’s ‘Thoughts on Music’' + ), + ( + 'seriously, ‘repair permissions’ is voodoo', + 'Seriously, ‘Repair Permissions’ Is Voodoo' + ), + ( + 'generalissimo francisco franco: still dead; kieren McCarthy: still a jackass', + 'Generalissimo Francisco Franco: Still Dead; Kieren McCarthy: Still a Jackass' + ), + ( + "O'Reilly should be untouched", + "O'Reilly Should Be Untouched" + ), + ( + "my name is o'reilly", + "My Name Is O'Reilly" + ), + ( + "WASHINGTON, D.C. SHOULD BE FIXED BUT MIGHT BE A PROBLEM", + "Washington, D.C. Should Be Fixed but Might Be a Problem" + ), + ( + "THIS IS ALL CAPS AND SHOULD BE ADDRESSED", + "This Is All Caps and Should Be Addressed" + ), + ( + "Mr McTavish went to MacDonalds", + "Mr McTavish Went to MacDonalds" + ), + ( + "this shouldn't\nget mangled", + "This Shouldn't\nGet Mangled" + ), + ( + "this is http://foo.com", + "This Is http://foo.com" + ) +) + +def test_all_caps_regex(): + """Test - all capitals regex""" + from titlecase import ALL_CAPS + assert bool(ALL_CAPS.match('THIS IS ALL CAPS')) is True + +def test_initials_regex(): + """Test - uppercase initals regex with A.B""" + from titlecase import UC_INITIALS + assert bool(UC_INITIALS.match('A.B')) is True + +def test_initials_regex_2(): + """Test - uppercase initals regex with A.B.""" + from titlecase import UC_INITIALS + assert bool(UC_INITIALS.match('A.B.')) is True + +def test_initials_regex_3(): + """Test - uppercase initals regex with ABCD""" + from titlecase import UC_INITIALS + assert bool(UC_INITIALS.match('ABCD')) is False + +def check_input_matches_expected_output(in_, out): + """Function yielded by test generator""" + try : + assert titlecase(in_) == out + except AssertionError: + print("%s != %s" % (titlecase(in_), out)) + raise + + +def test_input_output(): + """Generated tests""" + for data in TEST_DATA: + yield check_input_matches_expected_output, data[0], data[1] + + +if __name__ == "__main__": + import nose + nose.main() + -- cgit v1.2.3