DCausse has uploaded a new change for review.
https://gerrit.wikimedia.org/r/324389
Change subject: Use "docId" instead of "pageId"
......................................................................
Use "docId" instead of "pageId"
Change-Id: I74f1d11b8a3a62a2f643a80db77d6a044ba3201b
---
M jsondiff.py
M relcomp.py
2 files changed, 7 insertions(+), 7 deletions(-)
git pull ssh://gerrit.wikimedia.org:29418/wikimedia/discovery/relevanceForge
refs/changes/89/324389/1
diff --git a/jsondiff.py b/jsondiff.py
index 7f3651b..a273c46 100755
--- a/jsondiff.py
+++ b/jsondiff.py
@@ -5,7 +5,7 @@
# This program does diffs of two files with one JSON blob per line,
# outputting one color-coded HTML diff per line into a target directory.
# It performs a diff on the ordered list of results (based on a key value,
-# either pageId or title). It then notes differences within the details of
+# either docId or title). It then notes differences within the details of
# a given result.
#
# It has a number of hacks specific to diffing JSON from CirrusSearch
@@ -265,7 +265,7 @@
<b>score:</b> {0:}<br>\n'''.format(result['score'])
for item in sorted(result.keys()):
- if item not in ('pageId', 'score', 'title'):
+ if item not in ('docId', 'score', 'title'):
retval += html_result_item(result[item], item)
retval += '''\
@@ -469,10 +469,10 @@
parser.add_argument('-d', '--dir', dest='dir', default='./diffs/',
help='output directory, default is ./diffs/')
parser.add_argument("-t", "--bytitle", dest="bytitle",
action='store_true', default=False,
- help="use title rather than pageId to match results")
+ help="use title rather than docId to match results")
args = parser.parse_args()
- key = 'pageId'
+ key = 'docId'
if (args.bytitle):
key = 'title'
diff --git a/relcomp.py b/relcomp.py
index e2f71ea..87ceee2 100755
--- a/relcomp.py
+++ b/relcomp.py
@@ -218,7 +218,7 @@
class TopNDiff(Metric):
"""Percentage of query pairs where the top N results DO NOT have the
- same pageIds (ignoring order by default)
+ same docIds (ignoring order by default)
"""
__metaclass__ = ABCMeta
@@ -260,8 +260,8 @@
x["rows"] = list()
if "rows" not in y:
y["rows"] = list()
- x_ids = map((lambda r: r["pageId"]), x["rows"][0:self.topN])
- y_ids = map((lambda r: r["pageId"]), y["rows"][0:self.topN])
+ x_ids = map((lambda r: r["docId"]), x["rows"][0:self.topN])
+ y_ids = map((lambda r: r["docId"]), y["rows"][0:self.topN])
if self.sorted:
if len(x_ids) != len(y_ids):
--
To view, visit https://gerrit.wikimedia.org/r/324389
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: newchange
Gerrit-Change-Id: I74f1d11b8a3a62a2f643a80db77d6a044ba3201b
Gerrit-PatchSet: 1
Gerrit-Project: wikimedia/discovery/relevanceForge
Gerrit-Branch: master
Gerrit-Owner: DCausse <dcau...@wikimedia.org>
_______________________________________________
MediaWiki-commits mailing list
MediaWiki-commits@lists.wikimedia.org
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits
