def convert(self):
if len(self.cargs) < 3:
raise CommandError("Convert requires 2 arguments")
xml_path = self.cargs[1]
xslt_path = self.cargs[2]
out_file = self.cargs[3] if len(self.cargs) > 3 else None
xml_string = utils.readFile(xml_path)
xml_string = re.sub(ur"\bxmlns=", ur"xmlns2=", xml_string)
# TODO: remove this hack, only for odt conversion
# position 33% is like 'super' style
xml_string = re.sub(ur'"-33%', ur'"sub', xml_string)
xml_string = re.sub(ur'"33%', ur'"super', xml_string)
xslt_string = utils.readFile(xslt_path)
# replacements in the XSLT
comments, xslt_string = self.parse_xslt_directives(xslt_string, xml_string)
ret = str(dputils.get_xslt_transform(xml_string, xslt_string))
if out_file:
dputils.write_file(out_file, str(comments) + ret, encoding=None)
else:
print str(comments) + ret
return ret
def command_download(self):
ret = ur''
recordid = self.args[1]
unitid = ''
if len(self.args) > 2: unitid = self.args[2]
from digipal_text.models import TextContentXML
from digipal_text.views.viewer import get_fragment_extent, get_all_units
text_content_xml = TextContentXML.objects.get(id=recordid)
content = text_content_xml.content
suffix = ''
if unitid:
suffix = '-unit'
units = get_all_units(content, 'entry')
for unit in units:
if unit['unitid'] == unitid:
ret = ur'<root>%s</root>' % unit['content']
else:
ret = content
import regex
if ret is None:
ret = u''
# print repr(ret)
file_name = 'tcx%s%s.xml' % (text_content_xml.id, suffix)
from digipal.utils import write_file
write_file(file_name, ret)
print 'Written file %s ' % file_name
def convert(self):
if len(self.cargs) < 3:
raise CommandError('Convert requires 2 arguments')
xml_path = self.cargs[1]
xslt_path = self.cargs[2]
out_file = self.cargs[3] if len(self.cargs) > 3 else None
xml_string = utils.readFile(xml_path)
xml_string = re.sub(ur'\bxmlns=', ur'xmlns2=', xml_string)
# TODO: remove this hack, only for odt conversion
# position 33% is like 'super' style
xml_string = re.sub(ur'"-33%', ur'"sub', xml_string)
xml_string = re.sub(ur'"33%', ur'"super', xml_string)
xslt_string = utils.readFile(xslt_path)
# replacements in the XSLT
comments, xslt_string = self.parse_xslt_directives(xslt_string, xml_string)
ret = str(dputils.get_xslt_transform(xml_string, xslt_string))
if out_file:
dputils.write_file(out_file, str(comments) + ret, encoding=None)
else:
print str(comments) + ret
return ret
def command_autoconvert(self):
dry = self.is_dry_run()
from digipal_text.models import TextContentXML, TextAnnotation
from digipal_text.views import viewer
before = ur''
after = ur''
total = 0
converted = 0
for tcx in TextContentXML.objects.filter(
text_content__type__slug='transcription').order_by('id'):
total += 1
content = tcx.content
if not content: continue
tcx.convert()
if content != tcx.content:
converted += 1
text_name = u'#%s: %s [length diff = %s]' % (
tcx.id, tcx, abs(len(content) - len(tcx.content)))
print text_name
before += u'\n\n'
before += text_name
before += u'\n\n'
before += content.replace('\r', '\n')
after += u'\n\n'
after += text_name
after += u'\n\n'
after += tcx.content.replace('\r', '\n')
if 0:
html = ''
from difflib import HtmlDiff
diff = HtmlDiff(tabsize=2)
d = diff.make_table([content], [tcx.content])
html += u'<h2>%s</h2>' % text_name
html += d
if not dry:
tcx.save()
#break
#tcx.save()
dputils.write_file('before.txt', before)
dputils.write_file('after.txt', after)
print '%s converted out of %s texts' % (converted, total)
if dry:
print 'DRY RUN: no data was changed in the database.'
def command_download(self):
ret = ur''
recordid = self.args[1]
unitid = ''
if len(self.args) > 2: unitid = self.args[2]
from digipal_text.models import TextContentXML
from digipal_text.views.viewer import get_fragment_extent, get_all_units
text_content_xml = TextContentXML.objects.get(id=recordid)
content = text_content_xml.content
suffix = ''
if unitid:
suffix = '-unit'
units = get_all_units(content, 'entry')
for unit in units:
if unit['unitid'] == unitid:
ret = ur'<root>%s</root>' % unit['content']
else:
ret = content
import regex
if ret is None:
ret = u''
# ret = regex.sub(ur'(?musi)<span data-dpt="abbr">.*?</span>(<span data-dpt="exp">)', ur'\1', ret)
# ret = regex.sub(ur'(?musi)<span data-dpt="hi" data-dpt-rend="su[pb]">(.*?)</span>', ur'\1', ret)
# ret = regex.sub(ur'(?musi)<i>(.*?)</i>', ur'\1', ret)
# print repr(ret)
# for it in regex.findall('<span data-dpt="hi" data-dpt-rend="su[pb]">.*?</span>', ret):
# print repr(it)
# for it in regex.findall(ur'(?musi)qu[i1][i1]', ret):
# print repr(it)
if 0:
ret = regex.sub(ur'(?musi)<span data-dpt="hi" data-dpt-rend="sup">([^<]+)</span>', ur'<sup>\1</sup>', ret)
ret = regex.sub(ur'(?musi)<span data-dpt="hi" data-dpt-rend="sub">([^<]+)</span>', ur'<sub>\1</sub>', ret)
ret = regex.sub(ur'(?musi)<span data-dpt="lb" data-dpt-src="ms"></span>', ur'<br/>', ret)
ret = regex.sub(ur'(?musi)<span data-dpt="lb" data-dpt-src="prj"></span>', ur'<lb/>', ret)
ret = regex.sub(ur'(?musi)<span data-dpt="abbr">(.*?)</span>', ur'<abbr>\1</abbr>', ret)
ret = regex.sub(ur'(?musi)<span data-dpt="exp">(.*?)</span>', ur'<exp>\1</exp>', ret)
# print repr(ret)
file_name = 'tcx%s%s.xml' % (text_content_xml.id, suffix)
from digipal.utils import write_file
write_file(file_name, ret)
print 'Written file %s ' % file_name
def html2md(self):
if len(self.args) < 2:
print 'ERROR: missing path. Check help.'
exit()
path = self.args[1]
from digipal.views import doc
from django.utils.text import slugify
for path in utils.get_all_files_under(path, file_types='f', filters=self.options['filter'], extensions=['html', 'htm'], can_return_root=True):
info = doc.get_md_from_html(path)
target = os.path.join(doc.get_doc_root_path('digipal'), slugify(info['title']))+'.md'
if 'confluence-workbox' in target:
continue
utils.write_file(target, info['md'])
print '%s\n => %s' % (path, target)
for f in info['files']:
print ' + %s' % f
def html2md(self):
if len(self.args) < 2:
print 'ERROR: missing path. Check help.'
exit()
path = self.args[1]
from digipal.views import doc
from django.utils.text import slugify
for path in utils.get_all_files_under(path, file_types='f', filters=self.options['filter'], extensions=['html', 'htm'], can_return_root=True):
info = doc.get_md_from_html(path)
target = os.path.join(doc.get_doc_root_path('digipal'), slugify(info['title']))+'.md'
if 'confluence-workbox' in target:
continue
utils.write_file(target, info['md'])
print '%s\n => %s' % (path, target)
for f in info['files']:
print ' + %s' % f
