def print_statistics(): ''' Print the result of some queries. ''' kodiert = matches(faust.transcript_files(), kodiert_xp) encoded = matches(faust.transcript_files(), encoded_xp) kodiert_and_encoded = matches(faust.transcript_files(), kodiert_and_encoded_xp) print "kodiert: ", len(kodiert) print "encoded: ", len(encoded) print "kodiert und encoded: ", len(kodiert_and_encoded)
def print_statistics(): ''' Print the result of some queries. ''' kodiert = matches(faust.transcript_files(), kodiert_xp) encoded = matches(faust.transcript_files(), encoded_xp) kodiert_and_encoded = matches(faust.transcript_files(), kodiert_and_encoded_xp) print "kodiert: ", len(kodiert) print "encoded: ", len(encoded) print "kodiert und encoded: ", len(kodiert_and_encoded)
def invalid_facsimile_links():
''' Print all files with invalid facsimile links'''
faust_facsimiles = faust.facsimiles()
def facs_invalid(file):
xml = lxml.etree.parse(file)
urls = faust.xpath("//tei:facsimile/tei:graphic/@url")(xml)
for url in urls:
if url in faust_facsimiles: return True
return False
return filter(facs_invalid, faust.transcript_files())
def invalid_facsimile_links():
''' Print all files with invalid facsimile links'''
faust_facsimiles = faust.facsimiles()
def facs_invalid(file):
xml = lxml.etree.parse(file)
urls = faust.xpath("//tei:facsimile/tei:graphic/@url")(xml)
for url in urls:
if url in faust_facsimiles: return True
return False
return filter(facs_invalid, faust.transcript_files())
def correct_graphic_uris():
# take into account old GSA files
files = [f for f in faust.transcript_files() if '/gsa/' in f]
files.extend(xml_names_from_facsimiles())
for f in files:
rewrite_file = False
try:
xml = lxml.etree.parse(f)
except IOError:
# these should only be GSA files
print "(", f, " doesn't exist)"
continue
print f
graphics = graphic_xp(xml)
if len(graphics) == 0:
append_facsimile_element(xml)
# find the newly appended element
graphics = graphic_xp(xml)
brutal = False
if len(graphics) == 1:
brutal = True
for graphic in graphics:
old = graphic.attrib["url"]
new = correct_uri(old, brutal, f)
graphic.attrib["url"] = new
if new != old:
print " correcting: ", old, " -> ", new
rewrite_file = True
if rewrite_file:
rev_desc.add_change(xml, "system", "facsimile_adapted")
print " writing"
faust.tei_serialize(xml).write(f, encoding='UTF-8')
else:
print " not writing"
def correct_graphic_uris():
# take into account old GSA files
files = [f for f in faust.transcript_files() if '/gsa/' in f]
files.extend(xml_names_from_facsimiles())
for f in files:
rewrite_file = False
try:
xml = lxml.etree.parse(f)
except IOError:
# these should only be GSA files
print "(", f, " doesn't exist)"
continue
print f
graphics = graphic_xp(xml)
if len(graphics) == 0:
append_facsimile_element(xml)
# find the newly appended element
graphics = graphic_xp(xml)
brutal = False
if len(graphics) == 1:
brutal = True
for graphic in graphics:
old = graphic.attrib["url"]
new = correct_uri(old, brutal, f)
graphic.attrib["url"] = new
if new != old:
print " correcting: ", old, " -> ", new
rewrite_file = True
if rewrite_file:
rev_desc.add_change(xml, "system", "facsimile_adapted")
print " writing"
faust.tei_serialize(xml).write(f, encoding='UTF-8')
else:
print " not writing"
def count():
# status counters
status_keys = [key for (key, value) in faust.config.items("log-status")]
status_dict = {}
for key in status_keys:
status_dict[key] = 0
status_keys.sort()
status_unknown = 0
# iterate over all TEI documents
for xml_file in faust.transcript_files():
status = set()
try:
if faust.is_tei_document(xml_file):
xml = lxml.etree.parse(xml_file)
# iterate over all change records, searching for a status remark and select the last one
for change in change_xp(xml):
change_str = lxml.etree.tostring(change).lower().strip()
for candidate in [key.strip() for key in status_keys]:
if candidate in change_str: status.add(candidate)
except IOError:
sys.stderr.write("I/O error while extracting status from " +
xml_file + "\n")
except lxml.etree.XMLSyntaxError:
sys.stderr.write("XML error while extracting status from " +
xml_file + "\n")
if len(status) == 0:
# no status given
status_unknown += 1
else:
for s in status:
# increment relevant status entry
status_dict[s] += 1
return status_dict, status_unknown
def count():
# status counters
status_keys = [key for (key, value) in faust.config.items("log-status")]
status_dict = {}
for key in status_keys:
status_dict[key] = 0
status_keys.sort()
status_unknown = 0
# iterate over all TEI documents
for xml_file in faust.transcript_files():
status = set()
try:
if faust.is_tei_document(xml_file):
xml = lxml.etree.parse(xml_file)
# iterate over all change records, searching for a status remark and select the last one
for change in change_xp(xml):
change_str = lxml.etree.tostring(change).lower().strip()
for candidate in [key.strip() for key in status_keys]:
if candidate in change_str: status.add(candidate)
except IOError:
sys.stderr.write("I/O error while extracting status from " + xml_file + "\n")
except lxml.etree.XMLSyntaxError:
sys.stderr.write("XML error while extracting status from " + xml_file + "\n")
if len(status) == 0:
# no status given
status_unknown += 1
else:
for s in status:
# increment relevant status entry
status_dict[s] += 1
return status_dict, status_unknown
import query, faust, os.path, sys, os, shutil
from bn import relpath
def destination(file):
rel_f = relpath(file, faust.xml_dir)
return os.path.join(faust.xml_dir, 'attic', rel_f)
if __name__ == "__main__":
deleatur_transcripts = query.matches(faust.transcript_files(), query.deleatur_xp)
if '-e' in sys.argv:
print "executing"
for f in deleatur_transcripts:
print ' ' + f
print '-->' + destination(f)
print ''
dest_dir = os.path.dirname(destination(f))
print dest_dir
if not os.path.isdir(dest_dir):
os.makedirs(dest_dir)
shutil.move (f, destination(f))
else:
for f in deleatur_transcripts:
print ' ' + f
print '-->' + destination(f)
print ''
print "To execute, call with -e option"
def documentary_by_name(): textual = re.compile(r"transcript/.*/(.*)/\1.xml") def d_b_n(file): rel = faust.relative_path(file) return not textual.match(rel) return filter(d_b_n, faust.transcript_files())
#X u"//text()[contains(.,'\u231e')]", #8990
#X u"//text()[contains(.,'\u231f')]", #8991
#X u"//text()[contains(.,'\u2609')]", #9737
#X u"//text()[contains(.,'\u263d')]", #9789
u"//text()[contains(.,'\u0a50')]", #2640
#X u"//text()[contains(.,'\u2e13')]", #11795
#X u"//text()[contains(.,'\u2713')]", #10003
#X u"//text()[contains(.,'\u002B')]",
#X u"//text()[contains(.,'\u274C')]",
# u"//text()[contains(.,'\u00bc')]", # 188
# u"//text()[contains(.,'\u00bd')]", # 189
# u"//text()[contains(.,'\u00be')]", # 190
u"//text()[contains(.,'\u0391')]", # 913
u"//text()[contains(.,'\u0392')]", # 914
u"//text()[contains(.,'\u0393')]", # 915
u"//text()[contains(.,'\u0394')]", # 916
u"//text()[contains(.,'\u03b1')]", # 945
u"//text()[contains(.,'\u03b2')]", # 946
u"//text()[contains(.,'\u02e0')]", # 736
u"//text()[contains(.,'\u03b4')]", # 948
"//tei:change//comment()[contains(.,'Ritschel')]",
"//tei:change[@who='ritschel']"
]
bad_markup_disjunction = ' | '.join(bad_markup)
all_documents = set(map (os.path.dirname, faust.transcript_files()))
# print bad_markup_disjunction.encode('utf-8')
bad_documents = set(map (os.path.dirname, matches(faust.transcript_files(), bad_markup_disjunction)))
for d in all_documents.difference(bad_documents):
print '/'.join(d.split('/')[-2:])
def documentary_by_name(): textual = re.compile(r"transcript/.*/(.*)/\1.xml") def d_b_n(file): rel = faust.relative_path(file) return not textual.match(rel) return filter(d_b_n, faust.transcript_files())
def delete_empty_text_elements():
files = query.matches(faust.transcript_files(),
"//tei:text[not(.//text() or //tei:div[@type='template' or .//comment()])]")
xslt_trans = lxml.etree.XSLT(lxml.etree.parse("xsl/delete_empty_text_elements.xsl"))
del_txt = lambda t: tei_transform(t, xslt_trans)
transform_all(files, del_txt)
def transform_stages_to_changes():
xslt_trans = lxml.etree.XSLT(lxml.etree.parse("xsl/changes_to_stages.xsl"))
changes_to_stages = lambda t: tei_transform(t, xslt_trans)
transform_all(faust.transcript_files(), changes_to_stages)
import data_curation.query
import faust
#inscriptions_in_macrogenetic_files = data_curation.query.unique_values (faust.macrogenesis_files(),
# '//f:item/@uri[contains(.,"i_")]')
#inscriptions_in_transcripts = data_curation.query.unique_values (faust.transcript_files(),
# '//ge:stageNote/@xml:id[contains(.,"i_")]')
#bibliographic_sources_in_macrogenetic_files = data_curation.query.unique_values (faust.macrogenesis_files(),
# '//f:source/@uri')
for f in faust.transcript_files():
inscriptions = data_curation.query.unique_values ([f], '//ge:stageNote/@xml:id[contains(.,"i_")]')
for i in inscriptions:
print '%s/%s' % (f, i)
#print
#print 'Inscriptions in macrogenetic files: %i' % len(inscriptions_in_macrogenetic_files)
#for value in inscriptions_in_macrogenetic_files: print value
#print 'Inscriptions in transcript files: %i' % len(inscriptions_in_transcripts)
#for value in inscriptions_in_transcripts: print value
# need to prefix inscriptions_in_transcripts with transcript uri for this to work
#print 'References to i.s in macrogentic files without referent: %i' % len(inscriptions_in_macrogenetic_files - inscriptions_in_transcripts)
#print
#print 'Biligraphic sources in macrogenetic files: %i' % len(bibliographic_sources_in_macrogenetic_files)