Nilesh has uploaded a new change for review.
https://gerrit.wikimedia.org/r/72627
Change subject: Fixed errors in parser scripts
......................................................................
Fixed errors in parser scripts
Change-Id: Icb14b41875e3e86ba63495a46d31af2c27d56c51
---
M wikiparser/wikiparser.py
M wikiparser/wikiparser_db.py
M wikiparser/wikiparser_r.py
3 files changed, 10 insertions(+), 5 deletions(-)
git pull
ssh://gerrit.wikimedia.org:29418/mediawiki/extensions/WikidataEntitySuggester
refs/changes/27/72627/1
diff --git a/wikiparser/wikiparser.py b/wikiparser/wikiparser.py
index aab0f53..53483dd 100644
--- a/wikiparser/wikiparser.py
+++ b/wikiparser/wikiparser.py
@@ -41,10 +41,10 @@
toyield1 = str(statement['value'])
value =
str(statement['wikibase-entityid']['numeric-id']) if 'wikibase-entityid' in
statement else statement['string']
toyield2 = str(statement['value']) + "----" + value
- sys.stdout.write("||\t" + str(title) + "," +
toyield1.encode("utf-8", 'ignore') + "\n")
- sys.stdout.write("||\t" + str(title) + "," +
toyield2.encode("utf-8", 'ignore') + "\n")
sys.stdout.write("$$\t" + toyield1.encode("utf-8",
'ignore') + "\n")
sys.stdout.write("$$\t" + toyield2.encode("utf-8",
'ignore') + "\n")
+ sys.stdout.write("@@\t" + str(title) + "," +
toyield1.encode("utf-8", 'ignore') + "\n")
+ sys.stdout.write("@@\t" + str(title) + "," +
toyield2.encode("utf-8", 'ignore') + "\n")
except KeyError:
pass
except (KeyError, ValueError, TypeError) as e:
diff --git a/wikiparser/wikiparser_db.py b/wikiparser/wikiparser_db.py
index 953cda1..d614c09 100644
--- a/wikiparser/wikiparser_db.py
+++ b/wikiparser/wikiparser_db.py
@@ -66,10 +66,10 @@
toyield1 = str(statement['value'])
value =
str(statement['wikibase-entityid']['numeric-id']) if 'wikibase-entityid' in
statement else statement['string']
toyield2 = str(statement['value']) + "----" + value
- sys.stdout.write("||\t" + str(title) + "," +
toyield1.encode("utf-8", 'ignore') + "\n")
- sys.stdout.write("||\t" + str(title) + "," +
toyield2.encode("utf-8", 'ignore') + "\n")
sys.stdout.write("$$\t" + toyield1.encode("utf-8",
'ignore') + "\n")
sys.stdout.write("$$\t" + toyield2.encode("utf-8",
'ignore') + "\n")
+ sys.stdout.write("@@\t" + str(title) + "," +
toyield1.encode("utf-8", 'ignore') + "\n")
+ sys.stdout.write("@@\t" + str(title) + "," +
toyield2.encode("utf-8", 'ignore') + "\n")
except KeyError:
pass
elif page['ns'] == '120':
diff --git a/wikiparser/wikiparser_r.py b/wikiparser/wikiparser_r.py
index 52604d4..0593c0e 100644
--- a/wikiparser/wikiparser_r.py
+++ b/wikiparser/wikiparser_r.py
@@ -3,9 +3,14 @@
import sys
def main():
+ listout = open(sys.argv[1], "w")
for i in sys.stdin:
(key, value) = i.split("\t")
- sys.stdout.write(value + "\n")
+ if key == "@@":
+ sys.stdout.write(value)
+ else:
+ listout.write(value)
+ listout.close()
if __name__ == '__main__':
main()
--
To view, visit https://gerrit.wikimedia.org/r/72627
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: newchange
Gerrit-Change-Id: Icb14b41875e3e86ba63495a46d31af2c27d56c51
Gerrit-PatchSet: 1
Gerrit-Project: mediawiki/extensions/WikidataEntitySuggester
Gerrit-Branch: master
Gerrit-Owner: Nilesh <[email protected]>
_______________________________________________
MediaWiki-commits mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits