def create_csv_file(counts, analysis_type):
try:
if analysis_type == 'words':
return filehandler.write_to_csv(['word', 'frequency'],
counts['unique_words'],
'-word-counts.csv')
elif analysis_type == 'bigrams':
bigrams = []
for w in counts['bigrams']:
freq = w[1]
phrase = " ".join(w[0])
bigrams.append([phrase, freq])
return filehandler.write_to_csv(['bigram phrase', 'frequency'],
bigrams, '-bigram-counts.csv')
elif analysis_type == 'trigrams':
trigrams = []
for w in counts['trigrams']:
freq = w[1]
phrase = " ".join(w[0])
trigrams.append([phrase, freq])
return filehandler.write_to_csv(['trigram phrase', 'frequency'],
trigrams, '-trigram-counts.csv')
logger.error("Requested unknown csv type: %s", analysis_type)
except Exception as e:
logger.exception(e)
return render_template('no_results.html', tool_name='wordcounter')
def process_paste(text, has_header_row=True):
"""
Return results for a pasted table
"""
rows = text.splitlines()
csv_rows = []
for r in rows:
groups = re.findall(r'"(.*?)+"|\t', r)
if len(groups) == 3:
csv.rows.append((groups[0], groups[2]))
elif len(groups) == 1:
csv_rows.append((r.split('\t')[0], r.split('\t')[1]))
else:
return None
headers = csv_rows.pop(0) if has_header_row else ['source', 'target']
file_path = filehandler.write_to_csv(headers, csv_rows)
file_size = os.stat(file_path).st_size
logger.debug('[CTD] File size: %d bytes', file_size)
results = ctd.get_summary(file_path)
results['has_multiple_sheets'] = False
results['filename'] = 'Your Pasted Data'
filehandler.delete_files([file_path])
return results
def download(doc_id):
try:
logger.debug("Download %s", doc_id)
doc = mongo.find_document('samediff', doc_id)
headers = [
_('word'),
_('uses in') + ' ' + doc['filenames'][0],
_('uses in') + ' ' + doc['filenames'][1],
_('total uses')
]
rows = []
for f, w in doc['sameWords']:
doc1Count = next(f2 for f2, w2 in doc['mostFrequentDoc1']
if w == w2)
doc2Count = next(f2 for f2, w2 in doc['mostFrequentDoc2']
if w == w2)
rows.append([w, doc1Count, doc2Count, f])
for f, w in doc['diffWordsDoc1']:
rows.append([w, f, 0, f])
for f, w in doc['diffWordsDoc1']:
rows.append([w, 0, f, f])
# TODO: clean up file name
file_path = filehandler.write_to_csv(
headers, rows,
filehandler.generate_filename('csv', '', doc['filenames'][0],
doc['filenames'][1]), False)
logger.debug(' created csv to download at %s', file_path)
return filehandler.generate_csv(file_path)
except Exception as e:
logging.exception(e)
abort(400)
def process_paste(text, has_header_row=True):
"""
Return results for a pasted table
"""
rows = text.splitlines()
csv_rows = []
for r in rows:
groups = re.findall(r'"(.*?)+"|\t', r)
if len(groups) == 3:
csv.rows.append((groups[0], groups[2]))
elif len(groups) == 1:
csv_rows.append((r.split('\t')[0], r.split('\t')[1]))
else:
return None
headers = csv_rows.pop(0) if has_header_row else ['source', 'target']
file_path = filehandler.write_to_csv(headers, csv_rows)
file_size = os.stat(file_path).st_size
logger.debug('[CTD] File size: %d bytes', file_size)
results = ctd.get_summary(file_path)
results['has_multiple_sheets'] = False
results['filename'] = 'Your Pasted Data'
filehandler.delete_files([file_path])
return results
def create_csv_file(counts, analysis_type):
if analysis_type == 'words':
return filehandler.write_to_csv(['word', 'frequency'], counts['unique_words'], '-word-counts.csv')
elif analysis_type == 'bigrams':
bigrams = []
for w in counts['bigrams']:
freq = w[1]
phrase = " ".join(w[0])
bigrams.append([phrase, freq])
return filehandler.write_to_csv(['bigram phrase', 'frequency'], bigrams, '-bigram-counts.csv')
elif analysis_type == 'trigrams':
trigrams = []
for w in counts['trigrams']:
freq = w[1]
phrase = " ".join(w[0])
trigrams.append([phrase, freq])
return filehandler.write_to_csv(['trigram phrase', 'frequency'], trigrams, '-trigram-counts.csv')
logger.error("Requested unknown csv type: %s", analysis_type)
return None # if was an invalid analysis_type
def create_csv_file(counts, analysis_type):
if analysis_type == 'words':
return filehandler.write_to_csv(['word', 'frequency'],
counts['unique_words'],
'-word-counts.csv')
elif analysis_type == 'bigrams':
bigrams = []
for w in counts['bigrams']:
freq = w[1]
phrase = " ".join(w[0])
bigrams.append([phrase, freq])
return filehandler.write_to_csv(['bigram phrase', 'frequency'],
bigrams, '-bigram-counts.csv')
elif analysis_type == 'trigrams':
trigrams = []
for w in counts['trigrams']:
freq = w[1]
phrase = " ".join(w[0])
trigrams.append([phrase, freq])
return filehandler.write_to_csv(['trigram phrase', 'frequency'],
trigrams, '-trigram-counts.csv')
logger.error("Requested unknown csv type: %s", analysis_type)
return None # if was an invalid analysis_type
def download(doc_id):
try:
logger.debug("Download %s", doc_id)
doc = mongo.find_document('samediff', doc_id)
headers = [_('word'), _('uses in') +' ' + doc['filenames'][0], _('uses in') + ' ' + doc['filenames'][1], _('total uses')]
rows = []
for f, w in doc['sameWords']:
doc1Count = next(f2 for f2, w2 in doc['mostFrequentDoc1'] if w == w2)
doc2Count = next(f2 for f2, w2 in doc['mostFrequentDoc2'] if w == w2)
rows.append([w, doc1Count, doc2Count, f])
for f, w in doc['diffWordsDoc1']:
rows.append([w, f, 0, f])
for f, w in doc['diffWordsDoc1']:
rows.append([w, 0, f, f])
# TODO: clean up file name
file_path = filehandler.write_to_csv(headers, rows,
filehandler.generate_filename('csv', '', doc['filenames'][0], doc['filenames'][1]), False)
logger.debug(' created csv to download at %s', file_path)
return filehandler.generate_csv(file_path)
except Exception as e:
logging.exception(e)
abort(400)
