Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
gargantext
Project
Project
Details
Activity
Releases
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
humanities
gargantext
Commits
1099a7a8
Commit
1099a7a8
authored
Apr 28, 2016
by
delanoe
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
[FIX] Bug dates for WOS detected and fixed.
parent
dae9d611
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
20 additions
and
13 deletions
+20
-13
Ris.py
gargantext/util/parsers/Ris.py
+3
-10
_Parser.py
gargantext/util/parsers/_Parser.py
+17
-3
No files found.
gargantext/util/parsers/Ris.py
View file @
1099a7a8
...
@@ -11,7 +11,7 @@ class RISParser(Parser):
...
@@ -11,7 +11,7 @@ class RISParser(Parser):
# #super(Parser, self).__init__()
# #super(Parser, self).__init__()
# #super(Parser, self).__init__()
# #super(Parser, self).__init__()
# self._languages_cache = LanguagesCache() if language_cache is None else language_cache
# self._languages_cache = LanguagesCache() if language_cache is None else language_cache
_begin
=
6
_begin
=
6
_parameters
=
{
_parameters
=
{
...
@@ -29,13 +29,13 @@ class RISParser(Parser):
...
@@ -29,13 +29,13 @@ class RISParser(Parser):
}
}
def
parse
(
self
,
file
):
def
parse
(
self
,
file
):
hyperdata
=
{}
hyperdata
=
{}
last_key
=
None
last_key
=
None
last_values
=
[]
last_values
=
[]
# browse every line of the file
# browse every line of the file
for
line
in
file
:
for
line
in
file
:
if
len
(
line
)
>
2
:
if
len
(
line
)
>
2
:
# extract the parameter key
# extract the parameter key
parameter_key
=
line
[:
2
]
parameter_key
=
line
[:
2
]
if
parameter_key
!=
b
' '
and
parameter_key
!=
last_key
:
if
parameter_key
!=
b
' '
and
parameter_key
!=
last_key
:
...
@@ -60,11 +60,4 @@ class RISParser(Parser):
...
@@ -60,11 +60,4 @@ class RISParser(Parser):
print
(
error
)
print
(
error
)
# if a hyperdata object is left in memory, yield it as well
# if a hyperdata object is left in memory, yield it as well
if
hyperdata
:
if
hyperdata
:
# try:
# if hyperdata['date_to_parse']:
# print(hyperdata['date_to_parse'])
# except:
# pass
#
#print(hyperdata['title'])
yield
hyperdata
yield
hyperdata
gargantext/util/parsers/_Parser.py
View file @
1099a7a8
...
@@ -3,6 +3,7 @@ import dateutil.parser
...
@@ -3,6 +3,7 @@ import dateutil.parser
import
zipfile
import
zipfile
import
re
import
re
import
dateparser
as
date_parser
from
gargantext.util.languages
import
languages
from
gargantext.util.languages
import
languages
...
@@ -50,7 +51,7 @@ class Parser:
...
@@ -50,7 +51,7 @@ class Parser:
default
=
DEFAULT_DATE
default
=
DEFAULT_DATE
)
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
)
)
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
)
except
Exception
as
error
:
except
Exception
as
error
:
print
(
error
,
'
Parser Zotero,
Date not parsed for:'
,
date_string
)
print
(
error
,
'Date not parsed for:'
,
date_string
)
hyperdata
[
'publication_date'
]
=
datetime
.
datetime
.
now
()
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
)
hyperdata
[
'publication_date'
]
=
datetime
.
datetime
.
now
()
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
)
...
@@ -75,8 +76,21 @@ class Parser:
...
@@ -75,8 +76,21 @@ class Parser:
date_string
+=
":"
+
hyperdata
[
key
]
date_string
+=
":"
+
hyperdata
[
key
]
try
:
try
:
hyperdata
[
prefix
+
"_date"
]
=
dateutil
.
parser
.
parse
(
date_string
)
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
)
hyperdata
[
prefix
+
"_date"
]
=
dateutil
.
parser
.
parse
(
date_string
)
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
)
except
:
except
Exception
as
error
:
pass
try
:
print
(
error
,
date_string
)
# Date format: 1994 NOV-DEC
hyperdata
[
prefix
+
"_date"
]
=
date_parser
.
parse
(
str
(
date_string
)[:
8
])
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
)
except
Exception
as
error
:
try
:
print
(
error
)
# FIXME Date format: 1994 SPR
# By default, we take the year only
hyperdata
[
prefix
+
"_date"
]
=
date_parser
.
parse
(
str
(
date_string
)[:
4
])
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
)
except
Exception
as
error
:
print
(
error
)
else
:
else
:
print
(
"WARNING: Date unknown at _Parser level, using now()"
)
print
(
"WARNING: Date unknown at _Parser level, using now()"
)
hyperdata
[
'publication_date'
]
=
datetime
.
datetime
.
now
()
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
)
hyperdata
[
'publication_date'
]
=
datetime
.
datetime
.
now
()
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment