[sword-svn] r368 - trunk/modules/python

chrislit at crosswire.org chrislit at crosswire.org
Mon Aug 6 09:24:47 MST 2012 

Author: chrislit
Date: 2012-08-06 09:24:47 -0700 (Mon, 06 Aug 2012)
New Revision: 368

Modified:
   trunk/modules/python/usfm2osis.py
Log:
eliminated use of Plane 14 Language Tags, which required UCS-4 builds of Python in favor of U+FDD0-U+FDEF non-characters


Modified: trunk/modules/python/usfm2osis.py
===================================================================
--- trunk/modules/python/usfm2osis.py	2012-08-06 13:19:28 UTC (rev 367)
+++ trunk/modules/python/usfm2osis.py	2012-08-06 16:24:47 UTC (rev 368)
@@ -48,6 +48,25 @@
 # 1.x IMP output?
 # 1.x SWORD module output?, requiring SWORD bindings
 
+### Key to non-characters:
+# Used   : ﷐﷑﷒﷓﷔﷕﷖﷗﷘﷙﷚﷛﷜﷝﷞﷟
+# Unused : ﷠﷡﷢﷣﷤﷥﷦﷧﷨﷩﷪﷫﷬﷭﷮﷯
+# ﷐ book
+# ﷑ chapter
+# ﷒ verse
+# ﷓ paragraph 
+# ﷔ title
+# ﷕ ms1
+# ﷖ ms2
+# ﷗ ms3
+# ﷘ ms4
+# ﷙ ms5
+# ﷚ s1
+# ﷛ s2
+# ﷜ s3
+# ﷝ s4
+# ﷞ s5
+# ﷟ notes
 
 import sys, codecs, re
 from encodings.aliases import aliases
@@ -145,6 +164,7 @@
 osis2locBk = dict()
 loc2osisBk = dict()
 verbose = bool()
+ucs4 = (sys.maxunicode > 0xFFFF)
 
 """
 BEGIN PSF-licensed segment
@@ -206,7 +226,7 @@
         """
         global loc2osisBk, osis2locBk
         # \id_<CODE>_(Name of file, Book name, Language, Last edited, Date etc.)  ###TESTED###
-        osis = re.sub(r'\\id\s+([A-Z0-9]{3})\b\s*([^\\\n]*?)\n(.*)(?=\\id|$)', lambda m: u'󠁂<div type="book" osisID="' + bookDict[m.group(1)] + '">\n' + (('<!-- id comment - ' + m.group(2) + ' -->\n') if m.group(2) else '') +  m.group(3) + u'</div type="book">󠁂\n' , osis, flags=re.DOTALL)
+        osis = re.sub(r'\\id\s+([A-Z0-9]{3})\b\s*([^\\\n]*?)\n(.*)(?=\\id|$)', lambda m: u'﷐<div type="book" osisID="' + bookDict[m.group(1)] + '">\n' + (('<!-- id comment - ' + m.group(2) + ' -->\n') if m.group(2) else '') +  m.group(3) + u'</div type="book">﷐\n' , osis, flags=re.DOTALL)
         # keep a copy of the OSIS book abbreviation for below (\toc3 processing) to store for mapping localized book names to/from OSIS
         osisBook = re.search(r'\\id\s+([A-Z0-9]{3})', osis)
         if osisBook:
@@ -281,36 +301,44 @@
         supported: \mt#, \mte#, \ms#, \mr, \s#, \sr, \r, \rq...\rq*, \d, \sp
         """
         # \ms#_text...  ###TESTED###  ##NB: supports only \ms1 to \ms3
-        osis = re.sub(r'\\ms1?\s+(.+)', lambda m: u'󠀰<div type="majorSection"><title>' + m.group(1) + '</title>', osis)
-        osis = re.sub(u'(󠀰[^󠀰󠁂]+)', r'\1'+u'</div>󠀰\n', osis, re.DOTALL)
-        osis = re.sub(r'\\ms2\s+(.+)', lambda m: u'󠀱<div type="majorSection" n="2"><title>' + m.group(1) + '</title>', osis)
-        osis = re.sub(u'(󠀱[^󠀰󠁂󠀱]+)', r'\1'+u'</div>󠀱\n', osis, re.DOTALL)
-        osis = re.sub(r'\\ms3\s+(.+)', lambda m: u'󠀲<div type="majorSection" n="3"><title>' + m.group(1) + '</title>', osis)
-        osis = re.sub(u'(󠀲[^󠀰󠁂󠀱󠀲]+)', r'\1'+u'</div>󠀲\n', osis, re.DOTALL)
+        osis = re.sub(r'\\ms1?\s+(.+)', lambda m: u'﷕<div type="majorSection"><title>' + m.group(1) + '</title>', osis)
+        osis = re.sub(u'(﷕[^﷕﷐]+)', r'\1'+u'</div>﷕\n', osis, re.DOTALL)
+        osis = re.sub(r'\\ms2\s+(.+)', lambda m: u'﷖<div type="majorSection" n="2"><title>' + m.group(1) + '</title>', osis)
+        osis = re.sub(u'(﷖[^﷕﷐﷖]+)', r'\1'+u'</div>﷖\n', osis, re.DOTALL)
+        osis = re.sub(r'\\ms3\s+(.+)', lambda m: u'﷗<div type="majorSection" n="3"><title>' + m.group(1) + '</title>', osis)
+        osis = re.sub(u'(﷗[^﷕﷐﷖﷗]+)', r'\1'+u'</div>﷗\n', osis, re.DOTALL)
+        osis = re.sub(r'\\ms4\s+(.+)', lambda m: u'﷘<div type="majorSection" n="4"><title>' + m.group(1) + '</title>', osis)
+        osis = re.sub(u'(﷘[^﷕﷐﷖﷗﷘]+)', r'\1'+u'</div>﷘\n', osis, re.DOTALL)
+        osis = re.sub(r'\\ms5\s+(.+)', lambda m: u'﷙<div type="majorSection" n="5"><title>' + m.group(1) + '</title>', osis)
+        osis = re.sub(u'(﷙[^﷕﷐﷖﷗﷘﷙]+)', r'\1'+u'</div>﷙\n', osis, re.DOTALL)
 
         # \mr_text...
-        osis = re.sub(r'\\mr\s+(.+)', u'󠁄<title type="scope"><reference>'+r'\1</reference></title>', osis)
+        osis = re.sub(r'\\mr\s+(.+)', u'﷔<title type="scope"><reference>'+r'\1</reference></title>', osis)
 
         # \s#_text...  ###TESTED###  ##NB: supports only \s1 to \s3
-        osis = re.sub(r'\\s1?\s+(.+)', lambda m: u'󠀳<div type="section"><title>' + m.group(1) + '</title>', osis)
-        osis = re.sub(u'(󠀳[^󠀰󠁂󠀱󠀲󠀳]+)', r'\1'+u'</div>󠀳\n', osis, re.DOTALL)
+        osis = re.sub(r'\\s1?\s+(.+)', lambda m: u'﷚<div type="section"><title>' + m.group(1) + '</title>', osis)
+        osis = re.sub(u'(﷚[^﷕﷐﷖﷗﷘﷙﷚]+)', r'\1'+u'</div>﷚\n', osis, re.DOTALL)
         if relaxedConformance:
             osis = re.sub(r'\\ss\s+', r'\\s2 ', osis)
             osis = re.sub(r'\\sss\s+', r'\\s3 ', osis)
-        osis = re.sub(r'\\s2\s+(.+)', lambda m: u'󠀴<div type="subsection"><title>' + m.group(1) + '</title>', osis)
-        osis = re.sub(u'(󠀴[^󠀰󠁂󠀱󠀲󠀳󠀴]+)', r'\1'+u'</div>󠀴\n', osis, re.DOTALL)
-        osis = re.sub(r'\\s3\s+(.+)', lambda m: u'󠀵<div type="x-subSubSection"><title>' + m.group(1) + '</title>', osis)
-        osis = re.sub(u'(󠀵[^󠀰󠁂󠀱󠀲󠀳󠀴󠀵]+)', r'\1'+u'</div>󠀵\n', osis, re.DOTALL)
+        osis = re.sub(r'\\s2\s+(.+)', lambda m: u'﷛<div type="subsection"><title>' + m.group(1) + '</title>', osis)
+        osis = re.sub(u'(﷛[^﷕﷐﷖﷗﷘﷙﷚﷛]+)', r'\1'+u'</div>﷛\n', osis, re.DOTALL)
+        osis = re.sub(r'\\s3\s+(.+)', lambda m: u'﷜<div type="x-subSubSection"><title>' + m.group(1) + '</title>', osis)
+        osis = re.sub(u'(﷜[^﷕﷐﷖﷗﷘﷙﷚﷛﷜]+)', r'\1'+u'</div>﷜\n', osis, re.DOTALL)
+        osis = re.sub(r'\\s4\s+(.+)', lambda m: u'﷝<div type="x-subSubSubSection"><title>' + m.group(1) + '</title>', osis)
+        osis = re.sub(u'(﷝[^﷕﷐﷖﷗﷘﷙﷚﷛﷜﷝]+)', r'\1'+u'</div>﷝\n', osis, re.DOTALL)
+        osis = re.sub(r'\\s5\s+(.+)', lambda m: u'﷞<div type="x-subSubSubSubSection"><title>' + m.group(1) + '</title>', osis)
+        osis = re.sub(u'(﷞[^﷕﷐﷖﷗﷘﷙﷚﷛﷜﷝﷞]+)', r'\1'+u'</div>﷞\n', osis, re.DOTALL)
 
         # \sr_text...
-        osis = re.sub(r'\\sr\s+(.+)', u'󠁄<title type="scope"><reference>'+r'\1</reference></title>', osis)
+        osis = re.sub(r'\\sr\s+(.+)', u'﷔<title type="scope"><reference>'+r'\1</reference></title>', osis)
         # \r_text...
-        osis = re.sub(r'\\r\s+(.+)', u'󠁄<title type="parallel"><reference type="parallel">'+r'\1</reference></title>', osis)
+        osis = re.sub(r'\\r\s+(.+)', u'﷔<title type="parallel"><reference type="parallel">'+r'\1</reference></title>', osis)
         # \rq_text...\rq*
         osis = re.sub(r'\\rq\s+(.+?)\\rq\*', u'<reference type="source">'+r'\1</reference>', osis, flags=re.DOTALL)
 
         # \d_text...  ###TESTED###
-        osis = re.sub(r'\\d\s+(.+)', u'󠁄<title canonical="true" type="psalm">'+r'\1</title>', osis)
+        osis = re.sub(r'\\d\s+(.+)', u'﷔<title canonical="true" type="psalm">'+r'\1</title>', osis)
 
         # \sp_text...  ###TESTED###
         osis = re.sub(r'\\sp\s+(.+)', r'<speaker>\1</speaker>', osis)
@@ -329,7 +357,7 @@
         supported: \c, \ca...\ca*, \cl, \cp, \cd, \v, \va...\va*, \vp...\vp*
         """
         # \c_#  ###TESTED###
-        osis = re.sub(r'\\c\s+([^\s]+)\b(.+?)(?=(\\c\s+|</div type="book"))', lambda m: u'󠁃<chapter osisID="$BOOK$.' + m.group(1) + r'" sID="$BOOK$.' + m.group(1) + '"/>' + m.group(2) +  u'<chapter eID="$BOOK$.' + m.group(1) + u'"/>󠁐\n', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\c\s+([^\s]+)\b(.+?)(?=(\\c\s+|</div type="book"))', lambda m: u'﷑<chapter osisID="$BOOK$.' + m.group(1) + r'" sID="$BOOK$.' + m.group(1) + '"/>' + m.group(2) +  u'<chapter eID="$BOOK$.' + m.group(1) + u'"/>﷓\n', osis, flags=re.DOTALL)
 
         # \cp_#
         # \ca_#\ca*
@@ -349,13 +377,13 @@
         osis = re.sub(r'(<chapter [^<]+sID[^<]+/>.+?<chapter eID[^>]+/>)', replaceChapterNumber, osis, flags=re.DOTALL)
 
         # \cl_
-        osis = re.sub(r'\\cl\s+(.+)', u'󠁄<title>'+r'\1</title>', osis)
+        osis = re.sub(r'\\cl\s+(.+)', u'﷔<title>'+r'\1</title>', osis)
 
         # \cd_#   <--This # seems to be an error
-        osis = re.sub(r'\\cd\b\s+(.+)', u'󠁄<title type="x-description">'+r'\1</title>', osis)
+        osis = re.sub(r'\\cd\b\s+(.+)', u'﷔<title type="x-description">'+r'\1</title>', osis)
 
         # \v_#  ###TESTED###
-        osis = re.sub(r'\\v\s+([^\s]+)\b\s*(.+?)(?=(\\v\s+|</div type="book"|<chapter eID))', lambda m: u'󠁖<verse osisID="$BOOK$.$CHAP$.' + m.group(1) + r'" sID="$BOOK$.$CHAP$.' + m.group(1) + r'"/>' + m.group(2) +  r'<verse eID="$BOOK$.$CHAP$.' + m.group(1) + u'"/>󠁖\n', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\v\s+([^\s]+)\b\s*(.+?)(?=(\\v\s+|</div type="book"|<chapter eID))', lambda m: u'﷒<verse osisID="$BOOK$.$CHAP$.' + m.group(1) + r'" sID="$BOOK$.$CHAP$.' + m.group(1) + r'"/>' + m.group(2) +  r'<verse eID="$BOOK$.$CHAP$.' + m.group(1) + u'"/>﷒\n', osis, flags=re.DOTALL)
 
         # \vp_#\vp*
         # \va_#\va*
@@ -383,7 +411,7 @@
         supported: \p, \m, \pmo, \pm, \pmc, \pmr, \pi#, \mi, \nb, \cls, \li#, \pc, \pr, \ph#, \b
         """
         # \p(_text...)  ###TESTED###
-        osis = re.sub(r'\\p\s+(.*?)(?=(\\(m|p|nb|lit|cls|tr)|<chapter eID|</?div\b|<(p|closer)\b))', lambda m: u'󠁐<p>\n' + m.group(1) + u'󠁐</p>\n', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\p\s+(.*?)(?=(\\(m|p|nb|lit|cls|tr)|<chapter eID|</?div\b|<(p|closer)\b))', lambda m: u'﷓<p>\n' + m.group(1) + u'﷓</p>\n', osis, flags=re.DOTALL)
 
         # \pc(_text...)
         # \pr(_text...)
@@ -396,19 +424,19 @@
         # \mi(_text...)
         # \nb  ###TESTED###
         pType = {'pc':'x-center', 'pr':'x-right', 'm':'x-noindent', 'pmo':'x-embedded-opening', 'pm':'x-embedded', 'pmc':'x-embedded-closing', 'pmr':'x-right', 'pi':'x-indented-1', 'pi1':'x-indented-1', 'pi2':'x-indented-2', 'pi3':'x-indented-3', 'pi4':'x-indented-4', 'pi5':'x-indented-5', 'mi':'x-noindent-indented', 'nb':'x-nobreak'}
-        osis = re.sub(r'\\(pc|pr|m|pmo|pm|pmc|pmr|pi|pi1|pi2|pi3|pi4|pi5|mi|nb)\s+(.*?)(?=(\\(m|p|nb|lit|cls|tr)|<chapter eID|</?div\b|<(p|closer)\b))', lambda m: u'󠁐<p type="' + pType[m.group(1)]  + '">\n' + m.group(2) + u'󠁐</p>\n', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\(pc|pr|m|pmo|pm|pmc|pmr|pi|pi1|pi2|pi3|pi4|pi5|mi|nb)\s+(.*?)(?=(\\(m|p|nb|lit|cls|tr)|<chapter eID|</?div\b|<(p|closer)\b))', lambda m: u'﷓<p type="' + pType[m.group(1)]  + '">\n' + m.group(2) + u'﷓</p>\n', osis, flags=re.DOTALL)
 
         # \cls_text...
-        osis = re.sub(r'\\m\s+(.+?)(?=(\\(m|p|nb|lit|cls|tr)|<chapter eID|</?div\b|<(p|closer)\b))', lambda m: u'󠁐<closer>' + m.group(1) + u'󠁐</closer>\n', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\m\s+(.+?)(?=(\\(m|p|nb|lit|cls|tr)|<chapter eID|</?div\b|<(p|closer)\b))', lambda m: u'﷓<closer>' + m.group(1) + u'﷓</closer>\n', osis, flags=re.DOTALL)
 
         # \ph#(_text...)
         # \li#(_text...)  ###TESTED###
         osis = re.sub(r'\\ph\b\s*', r'\\li ', osis)
         osis = re.sub(r'\\ph(\d+)\b\s*', r'\\li\1 ', osis)
-        osis = re.sub(r'\\li\b\s*(.*?)(?=(['+u'󠁂󠁃󠁐󠁄'+r']|\\li[\d\s]|<lb\b|<title\b))', r'<item type="x-indent-1">\1</item>', osis, flags=re.DOTALL)
-        osis = re.sub(r'\\li(\d+)\b\s*(.*?)(?=(['+u'󠁂󠁃󠁐󠁄'+r']|\\li[\d\s]|<lb\b|<title\b))', r'<item type="x-indent-\1">\2</item>', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\li\b\s*(.*?)(?=(['+u'﷐﷑﷓﷔'+r']|\\li[\d\s]|<lb\b|<title\b))', r'<item type="x-indent-1">\1</item>', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\li(\d+)\b\s*(.*?)(?=(['+u'﷐﷑﷓﷔'+r']|\\li[\d\s]|<lb\b|<title\b))', r'<item type="x-indent-\1">\2</item>', osis, flags=re.DOTALL)
         osis = osis.replace('\n</item>', '</item>\n')
-        osis = re.sub(u'(<item [^󠁂󠁃󠁐󠁄]+</item>)', r'<list>\1</list>', osis, flags=re.DOTALL)
+        osis = re.sub(u'(<item [^﷐﷑﷓﷔]+</item>)', r'<list>\1</list>', osis, flags=re.DOTALL)
 
         # \b  ###TESTED###
         osis = re.sub(r'\\b\b\s?', r'<lb type="p"/>', osis)
@@ -425,23 +453,23 @@
         osis = re.sub(r'\\qs\b\s(.+?)\\qs\*', r'<l type="selah">\1</l>', osis, flags=re.DOTALL)
 
         # \q#(_text...)  ###TESTED###
-        osis = re.sub(r'\\q\b\s*(.*?)(?=(['+u'󠁂󠁃󠁐󠁄'+r']|\\q[\d\s]|<l\b|<lb\b|<title\b))', r'<l level="1">\1</l>', osis, flags=re.DOTALL)
-        osis = re.sub(r'\\q(\d+)\b\s*(.*?)(?=(['+u'󠁂󠁃󠁐󠁄'+r']|\\q[\d\s]|<l\b|<lb\b|<title\b))', r'<l level="\1">\2</l>', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\q\b\s*(.*?)(?=(['+u'﷐﷑﷓﷔'+r']|\\q[\d\s]|<l\b|<lb\b|<title\b))', r'<l level="1">\1</l>', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\q(\d+)\b\s*(.*?)(?=(['+u'﷐﷑﷓﷔'+r']|\\q[\d\s]|<l\b|<lb\b|<title\b))', r'<l level="\1">\2</l>', osis, flags=re.DOTALL)
 
         # \qr_text...
         # \qc_text...
         # \qm#(_text...)
         qType = {'qr':'x-right', 'qc':'x-center', 'qm':'x-embedded" level="1', 'qm1':'x-embedded" level="1', 'qm2':'x-embedded" level="2', 'qm3':'x-embedded" level="3', 'qm4':'x-embedded" level="4', 'qm5':'x-embedded" level="5'}
-        osis = re.sub(r'\\(qr|qc|qm\d+)\b\s*(.*?)(?=(['+u'󠁂󠁃󠁐󠁄'+r']|\\q[\d\s]|<l\b|<lb\b|<title\b))', lambda m: r'<l type="' + qType[m.group(1)] + '">' + m.group(2) + '</l>', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\(qr|qc|qm\d+)\b\s*(.*?)(?=(['+u'﷐﷑﷓﷔'+r']|\\q[\d\s]|<l\b|<lb\b|<title\b))', lambda m: r'<l type="' + qType[m.group(1)] + '">' + m.group(2) + '</l>', osis, flags=re.DOTALL)
 
         osis = osis.replace('\n</l>', '</l>\n')
-        osis = re.sub(u'(<l [^󠁂󠁃󠁐󠁄]+</l>)', r'<lg>\1</lg>', osis, flags=re.DOTALL)
+        osis = re.sub(u'(<l [^﷐﷑﷓﷔]+</l>)', r'<lg>\1</lg>', osis, flags=re.DOTALL)
 
         # \b  ###TESTED###
         osis = re.sub('(<lg>.+?</lg>)', lambda m: m.group(1).replace(r'<lb type="p"/>', r'</lg><lg>'), osis, flags=re.DOTALL) # re-handle \b that occurs within <lg>
 
         # \qa_text...
-        osis = re.sub(r'\\qa\s+(.+)', u'󠁄<title type="acrostic">'+r'\1</title>', osis)
+        osis = re.sub(r'\\qa\s+(.+)', u'﷔<title type="acrostic">'+r'\1</title>', osis)
 
         # \qac_text...\qac*
         osis = re.sub(r'\\qac\s+(.+?)\\qac\*', r'<hi type="acrostic">\1</hi>', osis, flags=re.DOTALL)
@@ -455,7 +483,7 @@
         supported: \tr, \th#, \thr#, \tc#, \tcr#
         """
         # \tr_
-        osis = re.sub(r'\\tr\b\s*(.*?)(?=(['+u'󠁂󠁃󠁐󠁄'+r']|\\tr\s|<lb\b|<title\b))', r'<row>\1</row>', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\tr\b\s*(.*?)(?=(['+u'﷐﷑﷓﷔'+r']|\\tr\s|<lb\b|<title\b))', r'<row>\1</row>', osis, flags=re.DOTALL)
 
         # \th#_text...
         # \thr#_text...
@@ -474,36 +502,36 @@
         note = re.sub(r'\\fdc\b\s(.+?)\\fdc\b\*', r'<seg editions="dc">\1</seg>', note)
 
         # \fq_  ###TESTED###
-        note = re.sub(r'\\fq\b\s(.+?)(?=(\\f|'+u'󠁆))', u'󠁆'+r'<catchWord>\1</catchWord>', note)
+        note = re.sub(r'\\fq\b\s(.+?)(?=(\\f|'+u'﷟))', u'﷟'+r'<catchWord>\1</catchWord>', note)
 
         # \fqa_  ###TESTED###
-        note = re.sub(r'\\fqa\b\s(.+?)(?=(\\f|'+u'󠁆))', u'󠁆'+r'<rdg type="alternate">\1</rdg>', note)
+        note = re.sub(r'\\fqa\b\s(.+?)(?=(\\f|'+u'﷟))', u'﷟'+r'<rdg type="alternate">\1</rdg>', note)
 
         # \ft_  ###TESTED###
         note = re.sub(r'\\ft\s', r'', note)
 
         # \fr_##SEP##
-        note = re.sub(r'\\fr\b\s(.+?)(?=(\\f|'+u'󠁆))', u'󠁆'+r'<reference>\1</reference>', note)
+        note = re.sub(r'\\fr\b\s(.+?)(?=(\\f|'+u'﷟))', u'﷟'+r'<reference>\1</reference>', note)
 
         # \fk_
-        note = re.sub(r'\\fk\b\s(.+?)(?=(\\f|'+u'󠁆))', u'󠁆'+r'<catchWord>\1</catchWord>', note)
+        note = re.sub(r'\\fk\b\s(.+?)(?=(\\f|'+u'﷟))', u'﷟'+r'<catchWord>\1</catchWord>', note)
 
         # \fl_
-        note = re.sub(r'\\fl\b\s(.+?)(?=(\\f|'+u'󠁆))', u'󠁆'+r'<label>\1</label>', note)
+        note = re.sub(r'\\fl\b\s(.+?)(?=(\\f|'+u'﷟))', u'﷟'+r'<label>\1</label>', note)
 
         # \fp_
         note = re.sub(r'\\fp\b\s(.+?)(?=(\\fp|$))', r'<p>\1</p>', note)
         note = re.sub(r'(<note\b[^>]*?>)(.*?)<p>', r'\1<p>\2</p><p>', note)
 
         # \fv_
-        note = re.sub(r'\\fv\b\s(.+?)(?=(\\f|'+u'󠁆))', u'󠁆'+r'<hi type="super">\1</hi>', note)
+        note = re.sub(r'\\fv\b\s(.+?)(?=(\\f|'+u'﷟))', u'﷟'+r'<hi type="super">\1</hi>', note)
 
         if relaxedConformance:
             note = note.replace(r'\ft*', r'')
             note = note.replace(r'\fq*', r'')
             note = note.replace(r'\fqa*', r'')
 
-        note = note.replace(u'󠁆', '')
+        note = note.replace(u'﷟', '')
         return note
 
 
@@ -513,10 +541,10 @@
         supported:\f...\f*, \fe...\fe*, \fr, \fk, \fq, \fqa, \fl, \fp, \fv, \ft, \fdc...\fdc*, \fm...\fm*
         """
         # \f_+_...\f*  ###TESTED###
-        osis = re.sub(r'\\f\s+([^\s\\]+)?\s*(.+?)\s*\\f\*', lambda m: r'<note' + ((' n=""') if (m.group(1) == u'-') else ('' if (m.group(1) == '+') else (' n="' + m.group(1) + '"'))) + ' placement="foot">' + m.group(2) + u'󠁆</note>', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\f\s+([^\s\\]+)?\s*(.+?)\s*\\f\*', lambda m: r'<note' + ((' n=""') if (m.group(1) == u'-') else ('' if (m.group(1) == '+') else (' n="' + m.group(1) + '"'))) + ' placement="foot">' + m.group(2) + u'﷟</note>', osis, flags=re.DOTALL)
 
         # \fe_+_...\fe*
-        osis = re.sub(r'\\fe\s+([^\s\\]+?)\s*(.+?)\s*\\fe\*', lambda m: r'<note' + ((' n=""') if (m.group(1) == u'-') else ('' if (m.group(1) == '+') else (' n="' + m.group(1) + '"'))) + ' placement="end">' + m.group(2) + u'󠁆</note>', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\fe\s+([^\s\\]+?)\s*(.+?)\s*\\fe\*', lambda m: r'<note' + ((' n=""') if (m.group(1) == u'-') else ('' if (m.group(1) == '+') else (' n="' + m.group(1) + '"'))) + ' placement="end">' + m.group(2) + u'﷟</note>', osis, flags=re.DOTALL)
 
         osis = re.sub(r'(<note\b[^>]*?>.*?</note>)', lambda m: processNote(m.group(1)), osis, flags=re.DOTALL)
 
@@ -530,31 +558,31 @@
         note = note.replace('\n', ' ')
 
         # \xot_refs...\xot*
-        note = re.sub(r'\\xot\b\s(.+?)\\xot\b\*', u'󠁆'+r'<seg editions="ot">\1</seg>', note)
+        note = re.sub(r'\\xot\b\s(.+?)\\xot\b\*', u'﷟'+r'<seg editions="ot">\1</seg>', note)
 
         # \xnt_refs...\xnt*
-        note = re.sub(r'\\xnt\b\s(.+?)\\xnt\b\*', u'󠁆'+r'<seg editions="nt">\1</seg>', note)
+        note = re.sub(r'\\xnt\b\s(.+?)\\xnt\b\*', u'﷟'+r'<seg editions="nt">\1</seg>', note)
 
         # \xdc_refs...\xdc*
-        note = re.sub(r'\\xdc\b\s(.+?)\\xdc\b\*', u'󠁆'+r'<seg editions="dc">\1</seg>', note)
+        note = re.sub(r'\\xdc\b\s(.+?)\\xdc\b\*', u'﷟'+r'<seg editions="dc">\1</seg>', note)
 
         # \xq_
-        note = re.sub(r'\\xq\b\s(.+?)(?=(\\x|'+u'󠁆))', u'󠁆'+r'<catchWord>\1</catchWord>', note)
+        note = re.sub(r'\\xq\b\s(.+?)(?=(\\x|'+u'﷟))', u'﷟'+r'<catchWord>\1</catchWord>', note)
 
         # \xt_  ###TESTED###
         note = re.sub(r'\\xt\s', r'', note)
 
         # \xo_##SEP##
-        note = re.sub(r'\\xo\b\s(.+?)(?=(\\x|'+u'󠁆))', u'󠁆'+r'<reference>\1</reference>', note)
+        note = re.sub(r'\\xo\b\s(.+?)(?=(\\x|'+u'﷟))', u'﷟'+r'<reference>\1</reference>', note)
 
         # \xk_
-        note = re.sub(r'\\xk\b\s(.+?)(?=(\\x|'+u'󠁆))', u'󠁆'+r'<catchWord>\1</catchWord>', note)
+        note = re.sub(r'\\xk\b\s(.+?)(?=(\\x|'+u'﷟))', u'﷟'+r'<catchWord>\1</catchWord>', note)
 
         if relaxedConformance:
             note = note.replace(r'\xt*', r'')
             note = note.replace(r'\xq*', r'')
 
-        note = note.replace(u'󠁆', '')
+        note = note.replace(u'﷟', '')
         return note
 
 
@@ -564,7 +592,7 @@
         supported: \\x...\\x*, \\xo, \\xk, \\xq, \\xt, \\xot...\\xot*, \\xnt...\\xnt*, \\xdc...\\xdc*
         """
         # \x_+_...\x*  ###TESTED###
-        osis = re.sub(r'\\x\s+([^\s]+?)\s+(.+?)\s*\\x\*', lambda m: r'<note' + ((' n=""') if (m.group(1) == u'-') else ('' if (m.group(1) == '+') else (' n="' + m.group(1) + '"'))) + ' type="crossReference"><reference>' + m.group(2) + u'</reference>󠁆</note>', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\x\s+([^\s]+?)\s+(.+?)\s*\\x\*', lambda m: r'<note' + ((' n=""') if (m.group(1) == u'-') else ('' if (m.group(1) == '+') else (' n="' + m.group(1) + '"'))) + ' type="crossReference"><reference>' + m.group(2) + u'</reference>﷟</note>', osis, flags=re.DOTALL)
 
         osis = re.sub(r'(<note [^>]*?type="crossReference"[^>]*>.*?</note>)', lambda m: processXref(m.group(1)), osis, flags=re.DOTALL)
 
@@ -610,7 +638,7 @@
         osis = re.sub(r'\\k\s+(.+?)\\k\*', r'<seg type="keyword">\1</seg>', osis, flags=re.DOTALL)
 
         # \lit
-        osis = re.sub(r'\\lit\s+(.*?)(?=(\\(m|p|nb|lit|cls|tr)|<chapter eID|</?div\b|<(p|closer)\b))', lambda m: u'󠁐<p type="x-liturgical">\n' + m.group(1) + u'󠁐</p>\n', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\lit\s+(.*?)(?=(\\(m|p|nb|lit|cls|tr)|<chapter eID|</?div\b|<(p|closer)\b))', lambda m: u'﷓<p type="x-liturgical">\n' + m.group(1) + u'﷓</p>\n', osis, flags=re.DOTALL)
 
         # \dc_...\dc*  #### TODO: Find an example---should this really be transChange?
         osis = re.sub(r'\\dc\b\s*(.+?)\\dc\*', r'<transChange type="added" editions="dc">\1</transChange>', osis, flags=re.DOTALL)
@@ -742,15 +770,15 @@
         supported: \ef...\ef*, \ex...\ex*, \esb...\esbe, \cat
         """
         # \ef...\ef*
-        osis = re.sub(r'\\ef\s+([^\s\\]+?)\s*(.+?)\s*\\ef\*', lambda m: r'<note' + ((' n=""') if (m.group(1) == u'-') else ('' if (m.group(1) == '+') else (' n="' + m.group(1) + '"'))) + ' type="study">' + m.group(2) + u'󠁆</note>', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\ef\s+([^\s\\]+?)\s*(.+?)\s*\\ef\*', lambda m: r'<note' + ((' n=""') if (m.group(1) == u'-') else ('' if (m.group(1) == '+') else (' n="' + m.group(1) + '"'))) + ' type="study">' + m.group(2) + u'﷟</note>', osis, flags=re.DOTALL)
         osis = re.sub(r'(<note\b[^>]*?>.*?</note>)', lambda m: processNote(m.group(1)), osis, flags=re.DOTALL)
 
         # \ex...\ex*
-        osis = re.sub(r'\\ex\s+([^\s]+?)\s+(.+?)\s*\\ex\*', lambda m: r'<note' + ((' n=""') if (m.group(1) == u'-') else ('' if (m.group(1) == '+') else (' n="' + m.group(1) + '"'))) + ' type="crossReference" subType="x-study"><reference>' + m.group(2) + u'</reference>󠁆</note>', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\ex\s+([^\s]+?)\s+(.+?)\s*\\ex\*', lambda m: r'<note' + ((' n=""') if (m.group(1) == u'-') else ('' if (m.group(1) == '+') else (' n="' + m.group(1) + '"'))) + ' type="crossReference" subType="x-study"><reference>' + m.group(2) + u'</reference>﷟</note>', osis, flags=re.DOTALL)
         osis = re.sub(r'(<note [^>]*?type="crossReference"[^>]*>.*?</note>)', lambda m: processXref(m.group(1)), osis, flags=re.DOTALL)
 
         # \esb...\esbex  ### TODO: this likely needs to go much earlier in the process
-        osis = re.sub(r'\\esb\b\s*(.+?)\\esbe\b\s*', '󠀰<div type="x-sidebar">\1</div>󠀰\n', osis, flags=re.DOTALL)
+        osis = re.sub(r'\\esb\b\s*(.+?)\\esbe\b\s*', '﷕<div type="x-sidebar">\1</div>﷕\n', osis, flags=re.DOTALL)
 
         # \cat_<TAG>\cat*
         osis = re.sub(r'\\cat\b\s+(.+?)\\cat\*', r'<index index="category" level1="\1"/>', osis)
@@ -790,14 +818,14 @@
 
 
         # fill in book & chapter values
-        bookChunks = osis.split(u'󠁂')
+        bookChunks = osis.split(u'﷐')
         osis = ''
         for bc in bookChunks:
             bookValue = re.search(r'<div type="book" osisID="([^"]+?)"', bc)
             if bookValue:
                 bookValue = bookValue.group(1)
                 bc = bc.replace('$BOOK$', bookValue)
-                chapChunks = bc.split(u'󠁃')
+                chapChunks = bc.split(u'﷑')
                 newbc = ''
                 for cc in chapChunks:
                     chapValue = re.search(r'<chapter osisID="[^\."]+\.([^"]+)', cc)
@@ -812,17 +840,17 @@
 
     def osisReorderAndCleanup(osis):
         # assorted re-orderings
-        osis = re.sub(u'(󠁐<chapter eID=.+?\n)(<verse eID=.+?>󠁖)\n?', r'\2\n\1', osis)
-        osis = re.sub(u'([󠀰󠀱󠀲]</div>)([^󠀰󠀱󠀲]*<chapter eID.+?>)', r'\2\1', osis)
-        osis = re.sub(u'(󠁐</p>\n?󠁐<p>)\n?(<verse eID=.+?>󠁖)\n?', r'\2\n\1\n', osis)
-        osis = re.sub(u'\n(<verse eID=.+?>󠁖)', r'\1\n', osis)
-        osis = re.sub(u'\n*(<l.+?>)(<verse eID=.+?>[󠁖\n]*<verse osisID=.+?>)', r'\2\1', osis)
+        osis = re.sub(u'(﷓<chapter eID=.+?\n)(<verse eID=.+?>﷒)\n?', r'\2\n\1', osis)
+        osis = re.sub(u'([﷕﷖﷗﷘﷙]</div>)([^﷕﷖﷗﷘﷙]*<chapter eID.+?>)', r'\2\1', osis)
+        osis = re.sub(u'(﷓</p>\n?﷓<p>)\n?(<verse eID=.+?>﷒)\n?', r'\2\n\1\n', osis)
+        osis = re.sub(u'\n(<verse eID=.+?>﷒)', r'\1\n', osis)
+        osis = re.sub(u'\n*(<l.+?>)(<verse eID=.+?>[﷒\n]*<verse osisID=.+?>)', r'\2\1', osis)
 
         # delete attributes from end tags (since they are invalid)
         osis = re.sub(r'(</[^\s>]+) [^>]*>', r'\1>', osis)
         osis = osis.replace(r'<lb type="p"/>', r'<lb/>')
         # delete Unicode tags
-        for c in u'󠁂󠁃󠁖󠁐󠁄󠀰󠀱󠀲󠀳󠀴󠀵':
+        for c in u'﷐﷑﷒﷓﷔﷕﷖﷗﷘﷙﷚﷛﷜﷝﷞﷟':
             osis = osis.replace(c, '')
 
         for endBlock in ['p', 'div', 'note', 'l', 'lg', 'chapter', 'verse']:

More information about the sword-cvs mailing list