From 237ae081dbade817f4a2033b6aa2d3cdeb15b8b2 Mon Sep 17 00:00:00 2001
From: Sébastien Dailly <sebastien@chimrod.com>
Date: Sat, 15 Nov 2014 21:22:30 +0100
Subject: Moved typogrify as plugin

---
 plugins/typogrify/titlecase/__init__.py | 101 ++++++++++++++++++++++++++++++++
 1 file changed, 101 insertions(+)
 create mode 100755 plugins/typogrify/titlecase/__init__.py

(limited to 'plugins/typogrify/titlecase/__init__.py')

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)
+
-- 
cgit v1.2.3