New minor release 4.5.17

dirkroorda · Mar 2, 2016 · 22c7003 · 22c7003
1 parent 2040641
commit 22c7003
Show file tree

Hide file tree

Showing 10 changed files with 22 additions and 8 deletions.
diff --git a/dist/laf-fabric-4.5.16.tar.gz b/dist/laf-fabric-4.5.16.tar.gz
diff --git a/dist/laf-fabric-4.5.17.tar.gz b/dist/laf-fabric-4.5.17.tar.gz
diff --git a/docs/conf.py b/docs/conf.py
@@ -25,7 +25,7 @@
 project = u'LAF Fabric'
 copyright = u'2013, Dirk Roorda'
 version = '4.5'
-release = '4.5.16'
+release = '4.5.17'
 exclude_patterns = ['_build']
 add_function_parentheses = True
 add_module_names = False

diff --git a/docs/conf.py.bck b/docs/conf.py.bck
@@ -25,7 +25,7 @@ master_doc = 'index'
 project = u'LAF Fabric'
 copyright = u'2013, Dirk Roorda'
 version = '4.5'
-release = '4.5.15'
+release = '4.5.16'
 exclude_patterns = ['_build']
 add_function_parentheses = True
 add_module_names = False

diff --git a/docs/texts/release-notes.rst b/docs/texts/release-notes.rst
@@ -1,5 +1,9 @@
 Release Notes
 #############
+4.5.17
+==========
+Small fixes in transcriptions (nun hafukha, setumah, petuhah, paseq).
+
 4.5.16
 ==========
 New languages for book names added: Russian, Turkish, Korean, Spanish, Swahili.

diff --git a/emdros2laf/settings.py b/emdros2laf/settings.py
@@ -7,7 +7,7 @@
 import argparse
 
 NAME = 'LAF-Fabric'
-VERSION = '4.5.16'
+VERSION = '4.5.17'
 APIREF = 'http://laf-fabric.readthedocs.org/en/latest/texts/API-reference.html'
 DEFAULT_DATA_DIR = 'laf-fabric-data'
 MAIN_CFG = 'laf-fabric.cfg'

diff --git a/etcbc/lib.py b/etcbc/lib.py
@@ -67,6 +67,7 @@ class Transcription(object):
         '52': "\u05C4", # upper dot = puncta_above
         '53': "\u05C5", # lower dot = puncta_below
         'ñ': "\u05C6\u0307", # nun hafukha
+        'Ñ': "\u05C6\u0307", # nun hafukha
         '>': "\u05D0", # alef
         'B': "\u05D1", # bet
         'G': "\u05D2", # gimel
@@ -107,6 +108,8 @@ class Transcription(object):
     swap_accent_pat = re.compile(r'(\A|[_&])([0-9][0-9])([' + hebrew_cons + r'])([:;,.EAIOU@]*)')
     remove_accent_pat = re.compile(r'((?:[0-9][0-9])|[,*])')
     remove_point_pat  = re.compile(r'((?:[0-9][0-9])|(?:\.[cf])|(?::[@AE])|[,.:;@AEIOU*])')
+    remove_psn_pat = re.compile(r'00[ _SPNÑñ]*')
+    remove_psq_pat = re.compile(r'(?:[ _]+05[ _]*)|(?:05[ _]+)')
     shin_pat = re.compile(r'[CF]')
     ph_simple_pat = re.compile(r'([ˈˌᵊᵃᵒᵉāo*])')
     noorigspace = re.compile('''
@@ -151,6 +154,9 @@ def __init__(self):
         self.hebrew_consonants = {Transcription.hebrew_mapping[x] for x in Transcription.hebrew_cons}
         self.hebrew_consonants.add('\u05E9')
         self.hebrew_mappingi = dict((v,k) for (k,v) in Transcription.hebrew_mapping.items() if k != '')
+        # special treatment needed for nun hafukha, since it is consists of two characters 
+        self.hebrew_mappingi['\u05C6'] = 'ñ'
+        self.hebrew_mappingi['\u0307'] = ''
 
     def _comp(s):
         for (d, c) in Transcription.decomp.items(): s = s.replace(d, c)
@@ -201,8 +207,8 @@ def suffix_and_finales(word):
     def _map_final(m): return m.group(1) + m.group(2).lower() + m.group(3)
     def _map_hebrew(m): return Transcription.hebrew_mapping.get(m.group(1), m.group(1))
     def _swap_accent(m): return m.group(1) + m.group(3) + m.group(4) + m.group(2)
-    def _remove_accent(m): return '00' if m.group(1) == '00' else ''
-    def _remove_point(m):  return '00' if m.group(1) == '00' else ''
+    def _remove_accent(m): return '00' if m.group(1) == '00' else '05' if m.group(1) == '05' else ''
+    def _remove_point(m):  return '00' if m.group(1) == '00' else '05' if m.group(1) == '05' else ''
     def _ph_simple(m): return 'å' if m.group(1) in 'āo' else ''
 
 # return unicodedata.normalize('NFKD', Transcription.trans_hebrew_pat.sub(Transcription._map_hebrew, nword))
@@ -216,6 +222,8 @@ def to_etcbc_v(word):
 
     def to_etcbc_c(word):
         word = Transcription.remove_point_pat.sub(Transcription._remove_point, word)
+        word = Transcription.remove_psn_pat.sub('00', word) # remove nun hafukha, setumah, petuhah at the end of a verse
+        word = Transcription.remove_psq_pat.sub(' ', word) # replace paseq with attached spaces by single space
         word = word.upper() # no final forms of consonants
         return Transcription.shin_pat.sub('#', word)
 

diff --git a/etcbc/text.py b/etcbc/text.py
@@ -556,6 +556,8 @@ def verse(self, bn, ch, vs, fmt='ha', html=True, verse_label=True, format_label=
         text = self.words(L.d('word', self._verses[bn][ch][vs]), fmt=fmt)
         if html:
             text = '<td class="{}">{}</td>'.format(fmt[0], h_esc(text))
+        else:
+            if not text.endswith('\n'): text += '\n'
 
         total = '{}{}{}'.format(vlabel, text, flabel)
         if html: total = '<table class="t"><tr>{}</tr></table>'.format(total)
@@ -576,7 +578,7 @@ def whole(self, fmt='ha', verse_labels=False, lang='en'):
                 wtext = make_rep(n)
                 reps.append(wtext)
             elif verse_labels and F.otype.v(n) == 'verse': reps.append('{}{} {}:{}  '.format(
-                '\n' if wtext and wtext[-1] != '\n' else '',
+                '\n' if reps and reps[-1] and reps[-1][-1] != '\n' else '',
                 self.book_name(L.u('book', n), lang=lang), F.chapter.v(n), F.verse.v(n),
             ))
         return ''.join(reps)

diff --git a/laf/settings.py b/laf/settings.py
@@ -3,7 +3,7 @@
 from .timestamp import Timestamp
 
 NAME = 'LAF-Fabric'
-VERSION = '4.5.16'
+VERSION = '4.5.17'
 APIREF = 'http://laf-fabric.readthedocs.org/en/latest/texts/API-reference.html'
 FEATDOC = 'https://shebanq.ancient-data.org/static/docs/featuredoc/texts/welcome.html'
 MAIN_CFG = 'laf-fabric.cfg'

diff --git a/setup.py b/setup.py
@@ -5,7 +5,7 @@
     package_data = {
         'emdros2laf': ['templates/*', 'xml/*'],
     },
-    version='4.5.16',
+    version='4.5.17',
     description='''Processor for Linguistic Annotation Framework ISO 24612:2012), applied to Biblical Hebrew''',
     author='Dirk Roorda',
     author_email='shebanq@ancient-data.org',