Modify the method duplicate_article since JHEP 06 (2012) 115 and JHEP 06...

Modify the method duplicate_article since JHEP 06 (2012) 115 and JHEP 06 (2015) 115 is valid (see cds 1443914 and 2003394).

modules/check_tools.py

@@ -8,34 +8,34 @@ import re
 import regex
 
 from gluon import current
-from plugin_dbui import (UNDEF, 
-                         UNDEF_ID, 
-                         get_id, 
+from plugin_dbui import (UNDEF,
+                         UNDEF_ID,
+                         get_id,
                          get_where_query)
 
 
 # syntax for the submission date YYYY-MM or YYYY-MM-DD
 REG_SUBMITTED = re.compile(regex.REG_SUBMITTED)
 
-# HTML code like > 
+# HTML code like >
 REG_HTML = re.compile('&[a-z]+;')
 
 
 def check_publication(row):
     """Check the publication fields.
-    
+
     @type row: gluon.dal.Row
     @param row: record defining a publication. Its contains the publications
     table as well as its reference tables.
-    
+
     @rtype: tuple
-    @return: 
+    @return:
         - the first element contains the list of message
         - the second one contains the list of duplicate ids.
-    
+
     """
     T, li, idset = current.T, [], set()
-    
+
     # status code
     if row.status.code == '???':
         text = T("The status is ???")
@@ -45,7 +45,7 @@ def check_publication(row):
     if row.categories.code == UNDEF:
         text = T("The category is undefined")
         li.append(text)
-    
+
     # team
     if row.publications.id_teams == UNDEF_ID:
         text = T("The team is undefined")
@@ -55,8 +55,8 @@ def check_publication(row):
     if row.publications.id_projects == UNDEF_ID:
         text = T("The project is undefined")
         li.append(text)
-               
-    # authors list    
+
+    # authors list
     if 'et al' in row.publications.authors:
         text = T("'et al.' in authors")
         li.append(text)
@@ -65,23 +65,23 @@ def check_publication(row):
     if row.teams.team in row.publications.authors_institute:
         text = T("The institute authors contains the team name?")
         li.append(text)
-        
+
     # submitted date
-    if not row.publications.submitted:                    
+    if not row.publications.submitted:
         text = T("Submitted date is not defined")
         li.append(text)
 
-    if row.publications.submitted:                    
-        if not REG_SUBMITTED.match(row.publications.submitted):                    
+    if row.publications.submitted:
+        if not REG_SUBMITTED.match(row.publications.submitted):
             text = T("Submitted date is not valid")
             li.append(text)
-    
+
     # publication URL
     if row.publications.publication_url:
         if 'pdf' not in row.publications.publication_url:
             text = T("Check that the publication URL corresponds to a pdf file.")
             li.append(text)
-            
+
     # latex syntax
     title = row.publications.title
     rules = "√" in title or \
@@ -90,39 +90,39 @@ def check_publication(row):
             ("->" in title) or \
             ("s**(1/2)" in title) or \
             REG_HTML.search(title)
-             
+
     if rules:
         text = T("Check latex syntax in the title")
         li.append(text)
-    
+
     # "Note :" in report number
     value = row.publications.report_numbers
     rules = "Note :" in value or \
             "Note:" in value or \
             ";" in value
-            
+
     if rules:
         text = T('Report numbers contains "Note :" or ";"')
         li.append(text)
-        
+
     # duplicate by origin
     ids = duplicate_origin(row.publications)
     if len(ids):
         idset = idset.union(ids)
         text = T("Entries with duplicate origin")
         li.append(text)
-    
+
     # specific fields for article
     if row.categories.usual == 'article':
-        
+
         if row.publications.id_publishers == UNDEF_ID:
             text = T("Publishers is not defined")
             li.append(text)
-            
+
         if not row.publications.volume:
             text = T("Volume number is not defined")
             li.append(text)
-            
+
         if not row.publications.pages:
             text = T("Pages range is not defined")
             li.append(text)
@@ -165,10 +165,10 @@ def check_publication(row):
             idset = idset.union(ids)
             text = T("Possible duplicate entries")
             li.append(text)
-    
+
     # specific fields for report
     if row.categories.usual == 'report':
-        
+
         if not row.publications.report_numbers:
             text = T("Report number is missing")
             li.append(text)
@@ -178,25 +178,25 @@ def check_publication(row):
             idset = idset.union(ids)
             text = T("Possible duplicate entries")
             li.append(text)
-    
+
     return (li, list(idset))
 
 
 def extend_ids(db, query, ids):
     """helper functions
-    
+
     @type db: gluon.dal.DAL
     @param db:
-    
+
     @type query: gluon.dal.query
-    @param query: 
-    
+    @param query:
+
     @type ids: list of string
     @param ids: the current list of ids
-    
+
     @note: the current list of publication ids will be extend by those
     corresponding to the C{query}. The id are unique in the list.
-    
+
     """
     set = db(query)
     if set.count():
@@ -205,47 +205,48 @@ def extend_ids(db, query, ids):
             if id not in ids:
                 ids.append(id)
 
-    
+
 def duplicate_article(publication):
     """Look for duplicate article.
     The comparison is performed on article published by the given team
     using the following criteria:
-    
+
         - title, publishers, volume and pages
         - publisher, volume and pages
         - publisher and title
-        
+
     @type publication: dict or gluon.storage.Storage
     @param publication: contains the publication fields and theirs values
-    
+
     @rtype: list
     @return: list of ids corresponding to duplicate entries
-    
+
     """
     ids = []
     db = current.globalenv['db']
-    
+
     qcat = (db.categories.code == 'ACL') | (db.categories.code == 'ACLN')
-    
+
     qmain = get_where_query(db.publications)
     qmain = ((qmain) & (qcat))
     qmain = ((qmain) & (db.publications.id_teams == publication['id_teams']))
     qmain = ((qmain) & (db.publications.id_publishers == publication['id_publishers']))
-    
+
     if 'id' in publication and publication['id']:
         qmain = ((qmain) & (db.publications.id != publication['id']))
-    
+
     # title, publishers, volume and pages
     query = ((qmain) & (db.publications.title == publication['title']))
     query = ((query) & (db.publications.volume == publication['volume']))
     query = ((query) & (db.publications.pages == publication['pages']))
     extend_ids(db, query, ids)
 
-    # publisher, volume and pages
+    # publisher, volume, pages and year
     query = ((qmain) & (db.publications.volume == publication['volume']))
     query = ((query) & (db.publications.pages == publication['pages']))
+    query = ((query) & (db.publications.year == publication['year']))
     extend_ids(db, query, ids)
-    
+
     # publisher and title
     query = ((qmain) & (db.publications.title == publication['title']))
     extend_ids(db, query, ids)
@@ -255,51 +256,51 @@ def duplicate_article(publication):
 
 def duplicate_conference(publication):
     """Look for duplicate talk / proceeding.
-    The comparison is performed on conference talk/proceeding published 
+    The comparison is performed on conference talk/proceeding published
     by the given team using the following criteria:
-    
+
         - title, conference title, conference date and conference town
         - title, conference date and conference town
         - title, conference title and conference town
-    
+
     @type publication: dict or gluon.storage.Storage
     @param publication: contains the publication fields and theirs values
-    
+
     @rtype: list
     @return: list of ids corresponding to duplicate entries
-    
+
     """
     ids = []
     db = current.globalenv['db']
-    
+
     qcat = (db.categories.code == 'ACTI') | \
            (db.categories.code == 'ACTN') | \
            (db.categories.code == 'COM')
-    
+
     qmain = get_where_query(db.publications)
     qmain = ((qmain) & (qcat))
     qmain = ((qmain) & (db.publications.id_teams == publication['id_teams']))
     qmain = ((qmain) & (db.publications.title == publication['title']))
-    
+
     if 'id' in publication and publication['id']:
         qmain = ((qmain) & (db.publications.id != publication['id']))
-    
+
     # title, conference title, conference date and conference town
     query = ((qmain) & (db.publications.conference_title == publication['conference_title']))
     query = ((query) & (db.publications.conference_dates == publication['conference_dates']))
     query = ((query) & (db.publications.conference_town == publication['conference_town']))
-    extend_ids(db, query, ids)        
+    extend_ids(db, query, ids)
 
     # title, conference date and conference town
     query = ((query) & (db.publications.conference_dates == publication['conference_dates']))
     query = ((query) & (db.publications.conference_town == publication['conference_town']))
-    extend_ids(db, query, ids)        
-    
+    extend_ids(db, query, ids)
+
     # title, conference title and conference town
     query = ((qmain) & (db.publications.conference_title == publication['conference_title']))
     query = ((query) & (db.publications.conference_town == publication['conference_town']))
-    extend_ids(db, query, ids)        
-    
+    extend_ids(db, query, ids)
+
     return ids
 
 
@@ -308,10 +309,10 @@ def duplicate_origin(publication):
 
     @type publication: dict or gluon.storage.Storage
     @param publication: contains the publication fields and theirs values
-    
+
     @rtype: list
     @return: list of ids corresponding to duplicate entries
-    
+
     """
     ids = []
     db = current.globalenv['db']
@@ -328,29 +329,29 @@ def duplicate_origin(publication):
     if set.count():
         for row in set.select():
             ids.append(str(row.id))
-    
+
     return ids
 
 
 def duplicate_report(publication):
     """Look for duplicate report.
-    The comparison is performed on report published by the given team 
+    The comparison is performed on report published by the given team
     using the following criteria:
-    
+
         - title
-    
+
     @type publication: dict or gluon.storage.Storage
     @param publication: contains the publication fields and theirs values
-    
+
     @rtype: list
     @return: list of ids corresponding to duplicate entries
-    
+
     """
     ids = []
     db = current.globalenv['db']
-    
+
     qcat = db.categories.code == 'AP'
-    
+
     qmain = get_where_query(db.publications)
     qmain = ((qmain) & (qcat))
     qmain = ((qmain) & (db.publications.id_teams == publication['id_teams']))
@@ -358,7 +359,7 @@ def duplicate_report(publication):
 
     if 'id' in publication and publication['id']:
         qmain = ((qmain) & (db.publications.id != publication['id']))
-    
-    extend_ids(db, qmain, ids)        
-            
-    return ids
\ No newline at end of file
+
+    extend_ids(db, qmain, ids)
+
+    return ids