catdog2/urlbot-native-trex
1
0
Fork 0
mirror of http://aero2k.de/t/repos/urlbot-native.git synced 2017-09-06 15:25:38 +02:00
Code Issues Releases Activity

testing str_sim() for (title, lev_url)

Browse Source
This commit is contained in:
urlbot
2014-10-05 23:39:51 +02:00
parent 09f96101f0
commit 6a916c701a
2 changed files with 38 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
strsim.py
View File

@@ -1,8 +1,9 @@
#!/usr/bin/python3
# -*- coding: utf-8 -*-
import re
def str_sim(a, b):
def str_sim(a, b, do_print=False):
a = a.lower()
b = b.lower()
@@ -17,14 +18,15 @@ def str_sim(a, b):
if a_parts[i] == b_parts[j]:
out[i][j] += 1
i = 0
for j in range(0, len(b_parts)):
print(' |'*i + ' '*2 + '.- ' + b_parts[j])
i += 1
print(' |'*i)
if do_print:
i = 0
for j in range(0, len(b_parts)):
print(' |'*i + ' '*2 + '.- ' + b_parts[j])
i += 1
print(' |'*i)
for i in range(0, len(a_parts)):
print(' ' + str(out[i]) + ' ' + a_parts[i])
for i in range(0, len(a_parts)):
print(' ' + str(out[i]) + ' ' + a_parts[i])
return out
@@ -38,26 +40,27 @@ def sum_array(array):
return _sum
def wrapper_print(a, b, comment=''):
ret = str_sim(a, b)
ret = str_sim(a, b, do_print=True)
if '' != comment: comment = ' ^ ' + comment
print('[%2dx%2d::%2d]%s' %(len(ret), len(ret[0]), sum_array(ret), comment))
pairs = (
(
'http://de.wikipedia.org/wiki/Monte_Kali_%28Heringen%29',
'Monte Kali (Heringen)'
),
(
'http://www.spiegel.de/politik/ausland/buddhisten-treffen-in-colombo-blitzender-moench-a-994447.html',
'Buddhisten-Treffen in Colombo: Blitzender Mönch - SPIEGEL ONLINE'
if '__main__' == __name__:
pairs = (
(
'http://de.wikipedia.org/wiki/Monte_Kali_%28Heringen%29',
'Monte Kali (Heringen)'
),
(
'http://www.spiegel.de/politik/ausland/buddhisten-treffen-in-colombo-blitzender-moench-a-994447.html',
'Buddhisten-Treffen in Colombo: Blitzender Mönch - SPIEGEL ONLINE'
)
)
)
wrapper_print('foo bar baz', 'foo bar boom')
wrapper_print('foo bar baz', 'foo bar boom')
for (url, title) in pairs:
wrapper_print(title, url, comment='raw')
url_no_proto = re.sub(r'https?://[^/]*/', '', url)
wrapper_print(title, url_no_proto, comment='no proto/domain')
url_no_proto_no_digits = re.sub(r'[0-9]*', '', url_no_proto)
wrapper_print(title, url_no_proto_no_digits, comment='no proto/domain/[0-9]')
for (url, title) in pairs:
wrapper_print(title, url, comment='raw')
url_no_proto = re.sub(r'https?://[^/]*/', '', url)
wrapper_print(title, url_no_proto, comment='no proto/domain')
url_no_proto_no_digits = re.sub(r'[0-9]*', '', url_no_proto)
wrapper_print(title, url_no_proto_no_digits, comment='no proto/domain/[0-9]')