def uploaded_file( filename ):
upload = app.config['UPLOAD_FOLDER']
project = request.args.get('project')
inp = InputFile(upload, project, filename)
filebase = inp.basename
filedir = inp.filedir
def get_tables( filedir, suffix = '.table.json'):
tablelist = list( filter( lambda x : x.endswith(suffix) , os.listdir( filedir ) ) )
#if len( tablelist ) == 0:
# analyze(path)
for tf in filter( lambda x : x.endswith(suffix) , os.listdir( filedir ) ):
with codecs.open( os.path.join(filedir,tf) ) as file:
table = json.load( file )
yield table #_to_df(table).to_html()
tables = get_tables( filedir, suffix = '.table.json')
dfs = (table_to_df(table).to_html() for table in tables )
#Create HTML
notices = ['Extraction Results for ' + filename, 'Ordered by lines']
headers = []
meta_data = []
for t in get_tables( filedir, suffix = '.table.json') :
meta_data.append( {'begin_line' : t['begin_line'], 'end_line' : t['end_line']} )
if 'header' in t:
headers.append(t['header'])
else:
headers.append('-')
chart_path = os.path.join(filedir, "chart" + '.png' )
return render_template('viewer.html',
title=TITLE + ' - ' + filename,
base_scripts=scripts, filename=filename, project=project,
css=css, notices = notices, tables = dfs, headers=headers, meta_data=meta_data, chart=chart_path)
#print i, underqualified, last_qualified, consecutive#, "" or row
test_file = "testcases/test_input1.txt"
test_string = read_lines( test_file )
rows = [row_feature(l) for l in test_string]
for b, e in filter_row_spans(rows, row_qualifies):
print(b, row_to_string(rows[b]), " --> ", e, row_to_string(rows[e]))
#for i in range(b,e):
# print i, len(rows[i]), row_to_string(rows[i])
print("#######################")
tables = indexed_tables_from_rows(rows)
for begin_line, t in tables.items():
df = table_to_df(t)
#for d in t['data']: print row_to_string(d)
for j in range(t['begin_line']-4, t['begin_line']):
pass
for j in range(t['begin_line'], t['end_line']):
pass #print len(rows[j]), test_string[j], "|".join([c['type']+'_'+c['subtype'] for c in rows[j]])
print(t['header'])
display(df)
try:
from IPython.display import display
test_file = "testcases/test_input6.txt"
