def main():
try:
record = '0002'
files_list = open("/media/sf_shared_with_ubuntu_guest_os/" + \
"mvol-00002-files-v2.txt",'r').readlines()
accession_set = []
output = {}
g = Grouping()
rep_labels = set([])
for n in files_list:
fullpath_dir = dirname(n)
relpath_dir = relpath(fullpath_dir, '/media/repo/repository/ac/')
accession = relpath_dir.split('/')[0]
i = AccessionDirectory(join('/media/repo/repository/ac/',
accession),
'/media/repo/repository/ac/')
a = AccessionItem(n,'/media/repo/repository/ac/')
the_file_path = a.get_file_path().strip()
a.set_canonical_filepath(a.find_canonical_filepath())
pattern = re_compile(r'(mvol)/(\w{4})/(\w{4})/(\w{4})')
matches = pattern.search(a.get_canonical_filepath())
if matches:
identifier = '-'.join([matches.group(1), matches.group(2),
matches.group(3), matches.group(4)])
limb_files_required = [('txt', r'{identifier}.txt$'.format(identifier = identifier)),
('struct', r'{identifier}.struct.txt$'.format(identifier = identifier)),
('pdf', r'{identifier}.pdf$'.format(identifier = identifier)),
('tiff', r'TIFF/%s_\d{4,}.tif$' % identifier),
('jpeg', r'JPEG/%s_\d{4,}.jpg$' % identifier),
('xml', r'XML/%s_\d{4,}.xml$' % identifier),
('alto', r'ALTO/%s_\d{4,}.\w{3,4}$' % identifier)]
prelimb_files_required = [('pdf', r'{identifier}.pdf$'.format(identifier = identifier)),
('txt', r'{identifier}.txt$'.format(identifier = identifier)),
('tiff', r'tif/\d{8,}.tif$'),
('jpeg', r'jpg/\d{8,}.jpg$'),
('xml', r'xml/\d{{8,}.xml$'),
('pos', r'pos/\d{8,}.pos$')]
page_num_file_parts = [r'(\d{8})', r'_(\d{4})']
files_required = []
files_required.extend(limb_files_required)
files_required.extend(prelimb_files_required)
n = g.does_it_need_a_new_item(identifier)
for tup in files_required:
pattern = re_compile(tup[1])
label = tup[0]
search = pattern.search(a.get_canonical_filepath())
if search:
check = True
is_page = False
for ppart in page_num_file_parts:
page_pattern = re_compile(ppart)
page_search = page_pattern.search(a.get_canonical_filepath())
if page_search:
is_page = True
n.add_page(a, label, page_search.group(1),
splitext(basename(a.get_canonical_filepath()))[0])
if not is_page:
n.add_representation(a, label)
else:
logging.error("could not match file {filename}".format(filename = the_file_path))
g.sort_items()
rep_labels = ['is there a .txt structural file','is there a -struct.xt structural file','is there a pdf file']
errors = {}
errors_txt_file = "errors-%s.txt" % record
error_file = open(errors_txt_file,"a")
mvol_csv = "mvol-%s.csv" % record
with open(mvol_csv, 'w') as csvfile:
recwriter = csv.writer(csvfile, delimiter=',',
quotechar='"', quoting=csv.QUOTE_ALL)
header = ['issue identifier']
header.extend(rep_labels)
header.extend(['which accessions have files for this issue'])
header.extend(['were page files found','number of pages in structural metadata', 'number of pages on disk'])
recwriter.writerow(header)
for n in g.items:
repnum = ""
rowstring = []
if 'Thum' in n.identifier or 'tif' in n.identifier or 'test' in n.identifier:
continue
rowstring.append(n.identifier)
for rep in ['struct', 'txt', 'pdf']:
l = getattr(n, rep, None)
if l:
num_value = "Y"
else:
num_value = "N"
try:
errors.get(n.identifier).append("missing {rep}".format(rep = rep))
except:
errors[n.identifier] = ["missing {rep}".format(rep = rep)]
error_file.write("\"{id}\",\"missing {rep}\"\n".format(id = identifier, rep = rep))
rowstring.append(str(num_value))
s1 = getattr(n,'struct',None)
s2 = getattr(n,'txt',None)
if s1:
struct_mdata_files = s1
elif s2:
struct_mdata_files = s2
if isinstance(struct_mdata_files, list):
struct_mdata_files = [x.get_file_path().strip() for x in struct_mdata_files]
else:
struct_mdata_files = [x.get_file_path().strip()]
objids = []
for struct_mdata_file in struct_mdata_files:
try:
fp = open(struct_mdata_file,'r')
lines = fp.readlines()
relevant_lines = lines[1:]
objids = [x.replace('\t','').strip('\n') for x in relevant_lines]
except UnicodeDecodeError:
stderr.write("{mfile} couldn't be opened\n".format(mfile = struct_mdata_file))
objids = []
rowstring.append(','.join(list(n.accessions)))
are_pages = 'Y' if len(n.pages) > 0 else 'N'
rowstring.append(are_pages)
rowstring.append(len(objids))
rowstring.append(len(n.pages))
if len(n.pages) == 0:
try:
errors.get(n.identifier).append("no pages")
except:
errors[n.identifier] = ["no pages"]
error_file.write("\"{id}\",\"no pages\"\n".format(id = identifier))
recwriter.writerow(rowstring)
pages_csv = "%s-pages.csv" % n.identifier
pages_errors_csv = "%s-pages-errors.csv" % n.identifier
with open(pages_csv,'w') as pagescsvfile:
pageswriter = csv.writer(pagescsvfile, delimiter=',',quotechar='"', quoting=csv.QUOTE_ALL)
pageswriter.writerow(['object','issue identifier',
'is there an ocr file',
'is there a jpeg file',
'is there a tiff file'])
sorted_pages = sorted(n.pages)
for p in sorted_pages:
error_row = []
ocr_there = "Y" if getattr(p,'pos',None) or getattr(p,'alto',None) or getattr(p, 'xml',None) else "N"
jpeg_there = "Y" if getattr(p, 'jpeg',None) else "N"
tiff_there = "Y" if getattr(p, 'tiff',None) else "N"
pageswriter.writerow([p.objectpage, n.identifier,
ocr_there, jpeg_there, tiff_there])
errors_csv_filename = "errors-%s" % record
with open(errors_csv_filename, "w") as errorfile:
newrecwriter = csv.writer(errorfile, delimiter=',',
quotechar='"', quoting=csv.QUOTE_ALL)
for key,value in errors.items():
newrecwriter.writerow([key,','.join(value)])
return 0
except KeyboardInterrupt:
return 131
def main():
try:
files_list = open("/media/sf_shared_with_ubuntu_guest_os/" + \
"mvol-0001-files.txt",'r').readlines()
accession_set = []
output = {}
g = Grouping()
rep_labels = set([])
for n in files_list:
fullpath_dir = dirname(n)
relpath_dir = relpath(fullpath_dir, '/media/repo/repository/ac/')
accession = relpath_dir.split('/')[0]
i = AccessionDirectory(
join('/media/repo/repository/ac/', accession),
'/media/repo/repository/ac/')
a = AccessionItem(n, '/media/repo/repository/ac/')
the_file_path = a.get_file_path().strip()
a.set_canonical_filepath(a.find_canonical_filepath())
pattern = re_compile(r'(mvol)/(\w{4})/(\w{4})/(\w{4})')
matches = pattern.search(a.get_canonical_filepath())
if matches:
identifier = '-'.join([
matches.group(1),
matches.group(2),
matches.group(3),
matches.group(4)
])
limb_files_required = [
('dc',
r'{identifier}.dc.xml$'.format(identifier=identifier)),
('dc-fits', r'{identifier}.dc.xml.fits.xml$'.format(
identifier=identifier)),
('mets-fits', r'{identifier}.mets.xml.fits.xml$'.format(
identifier=identifier)),
('mets',
r'{identifier}.mets.xml$'.format(identifier=identifier)),
('txt',
r'{identifier}.txt$'.format(identifier=identifier)),
('txt-fits', r'{identifier}.txt.fits.xml$'.format(
identifier=identifier)),
('struct', r'{identifier}.struct.txt$'.format(
identifier=identifier)),
('struct-fits',
r'{identifier}.struct.txt.fits.xml$'.format(
identifier=identifier)),
('pdf',
r'{identifier}.pdf$'.format(identifier=identifier)),
('pdf-fits', r'{identifier}.pdf.fits.xml$'.format(
identifier=identifier)),
('tiff', r'TIFF/%s_\d{4}.tif$' % identifier),
('tiff-fits', r'TIFF/%s_\d{4}.tif.fits.xml$' % identifier),
('jpeg', r'JPEG/%s_\d{4}.jpg$' % identifier),
('jpeg-fits', r'JPEG/%s_\d{4}.jpg.fits.xml$' % identifier),
('alto', r'ALTO/%s_\d{4}.\w{3,4}$' % identifier),
('alto-fits',
r'ALTO/%s_\d{4}.\w{3,4}.fits.xml$' % identifier)
]
prelimb_files_required = [
('dc',
r'{identifier}.dc.xml$'.format(identifier=identifier)),
('dc-fits', r'{identifier}.dc.xml.fits.xml$'.format(
identifier=identifier)),
('pdf',
r'{identifier}.pdf$'.format(identifier=identifier)),
('pdf-fits', r'{identifier}.pdf.fits.xml$'.format(
identifier=identifier)),
('txt',
r'{identifier}.txt$'.format(identifier=identifier)),
('txt-fits', r'{identifier}.txt.fits.xml$'.format(
identifier=identifier)), ('tif', r'tif/\d{8}.tif$'),
('tif-fits', 'tif/\d{8}.tif.fits.xml$'),
('jpeg', r'jpg/\d{8}.jpg$'),
('jpg-fits', r'jpg/\d{8}.jpg.fits.xml$'),
('pos', r'pos/\d{8}.pos$'),
('pos-fits', r'pos/\d{8}.pos.fits.xml$')
]
page_num_file_parts = [r'(\d{8})', r'_(\d{4})']
files_required = []
files_required.extend(limb_files_required)
files_required.extend(prelimb_files_required)
n = g.does_it_need_a_new_item(identifier)
for tup in files_required:
pattern = re_compile(tup[1])
label = tup[0]
search = pattern.search(a.get_canonical_filepath())
if search:
check = True
is_page = False
for ppart in page_num_file_parts:
page_pattern = re_compile(ppart)
page_search = page_pattern.search(
a.get_canonical_filepath())
if page_search:
is_page = True
n.add_page(a, label, page_search.group(1))
if not is_page:
rep_labels.add(label)
n.add_representation(a, label)
else:
logging.error("could not match file {filename}".format(
filename=the_file_path))
g.sort_items()
rep_labels = list(rep_labels)
with open('mvol-0001.csv', 'w') as csvfile:
recwriter = csv.writer(csvfile,
delimiter=',',
quotechar='"',
quoting=csv.QUOTE_ALL)
header = ['identifier']
header.extend(rep_labels)
header.extend(['accession'])
header.extend(['numpages'])
recwriter.writerow(header)
for n in g.items:
repnum = ""
rowstring = []
rowstring.append(n.identifier)
for rep in n.representations:
if getattr(n, rep):
repnum = len(getattr(n, rep))
else:
print(getattr(n, rep))
repnum = 0
rowstring.append(str(repnum))
rowstring.append(','.join(list(n.accessions)))
rowstring.append(str(len(n.pages)))
recwriter.writerow(rowstring)
recwriter.close()
return 0
except KeyboardInterrupt:
return 131
def main():
try:
files_list = open("/media/sf_shared_with_ubuntu_guest_os/" + \
"mvol-0001-files.txt",'r').readlines()
accession_set = []
output = {}
g = Grouping()
rep_labels = set([])
for n in files_list:
fullpath_dir = dirname(n)
relpath_dir = relpath(fullpath_dir, '/media/repo/repository/ac/')
accession = relpath_dir.split('/')[0]
i = AccessionDirectory(join('/media/repo/repository/ac/',
accession),
'/media/repo/repository/ac/')
a = AccessionItem(n,'/media/repo/repository/ac/')
the_file_path = a.get_file_path().strip()
a.set_canonical_filepath(a.find_canonical_filepath())
pattern = re_compile(r'(mvol)/(\w{4})/(\w{4})/(\w{4})')
matches = pattern.search(a.get_canonical_filepath())
if matches:
identifier = '-'.join([matches.group(1), matches.group(2),
matches.group(3), matches.group(4)])
limb_files_required = [('dc',r'{identifier}.dc.xml$'.format(identifier = identifier)),
('dc-fits',r'{identifier}.dc.xml.fits.xml$'.format(identifier = identifier)),
('mets-fits', r'{identifier}.mets.xml.fits.xml$'.format(identifier = identifier)),
('mets', r'{identifier}.mets.xml$'.format(identifier = identifier)),
('txt', r'{identifier}.txt$'.format(identifier = identifier)),
('txt-fits', r'{identifier}.txt.fits.xml$'.format(identifier = identifier)),
('struct', r'{identifier}.struct.txt$'.format(identifier = identifier)),
('struct-fits', r'{identifier}.struct.txt.fits.xml$'.format(identifier = identifier)),
('pdf', r'{identifier}.pdf$'.format(identifier = identifier)),
('pdf-fits', r'{identifier}.pdf.fits.xml$'.format(identifier = identifier)),
('tiff', r'TIFF/%s_\d{4}.tif$' % identifier),
('tiff-fits', r'TIFF/%s_\d{4}.tif.fits.xml$' % identifier),
('jpeg', r'JPEG/%s_\d{4}.jpg$' % identifier),
('jpeg-fits', r'JPEG/%s_\d{4}.jpg.fits.xml$' % identifier),
('alto', r'ALTO/%s_\d{4}.\w{3,4}$' % identifier),
('alto-fits', r'ALTO/%s_\d{4}.\w{3,4}.fits.xml$' % identifier)]
prelimb_files_required = [('dc', r'{identifier}.dc.xml$'.format(identifier = identifier)),
('dc-fits', r'{identifier}.dc.xml.fits.xml$'.format(identifier = identifier)),
('pdf', r'{identifier}.pdf$'.format(identifier = identifier)),
('pdf-fits', r'{identifier}.pdf.fits.xml$'.format(identifier = identifier)),
('txt', r'{identifier}.txt$'.format(identifier = identifier)),
('txt-fits', r'{identifier}.txt.fits.xml$'.format(identifier = identifier)),
('tif', r'tif/\d{8}.tif$'),
('tif-fits', 'tif/\d{8}.tif.fits.xml$'),
('jpeg', r'jpg/\d{8}.jpg$'),
('jpg-fits', r'jpg/\d{8}.jpg.fits.xml$'),
('pos', r'pos/\d{8}.pos$'),
('pos-fits', r'pos/\d{8}.pos.fits.xml$')]
page_num_file_parts = [r'(\d{8})', r'_(\d{4})']
files_required = []
files_required.extend(limb_files_required)
files_required.extend(prelimb_files_required)
n = g.does_it_need_a_new_item(identifier)
for tup in files_required:
pattern = re_compile(tup[1])
label = tup[0]
search = pattern.search(a.get_canonical_filepath())
if search:
check = True
is_page = False
for ppart in page_num_file_parts:
page_pattern = re_compile(ppart)
page_search = page_pattern.search(a.get_canonical_filepath())
if page_search:
is_page = True
n.add_page(a, label, page_search.group(1))
if not is_page:
rep_labels.add(label)
n.add_representation(a, label)
else:
logging.error("could not match file {filename}".format(filename = the_file_path))
g.sort_items()
rep_labels = list(rep_labels)
with open('mvol-0001.csv', 'w') as csvfile:
recwriter = csv.writer(csvfile, delimiter=',',
quotechar='"', quoting=csv.QUOTE_ALL)
header = ['identifier']
header.extend(rep_labels)
header.extend(['accession'])
header.extend(['numpages'])
recwriter.writerow(header)
for n in g.items:
repnum = ""
rowstring = []
rowstring.append(n.identifier)
for rep in n.representations:
if getattr(n, rep):
repnum = len(getattr(n, rep))
else:
print(getattr(n,rep))
repnum = 0
rowstring.append(str(repnum))
rowstring.append(','.join(list(n.accessions)))
rowstring.append(str(len(n.pages)))
recwriter.writerow(rowstring)
recwriter.close()
return 0
except KeyboardInterrupt:
return 131
