Clean the code.

controllers/harvest.py

@@ -7,6 +7,7 @@ import traceback
 from gluon import current
 from gluon.restricted import RestrictedError
 from harvest_tools import (build_harvester_tool,
+                           DRY_RUN,
                            format_author_fr,
                            family_name_fr,
                            ToolException)
@@ -22,7 +23,7 @@ from plugin_dbui import (get_id,
                          to_formPanel,
                          UNDEF_ID)
 
-DRY_RUN = T("dry run")
+MODE_DRY_RUN = T(DRY_RUN)
 MSG_NO_REG_INSTITUTE = T("Preference REG_INSTITUTE is not defined.")
 MSG_NO_HARVESTER = T("No harvesters for your selection !!!")
 
@@ -62,7 +63,7 @@ def free_run():
                           selector.id_categories,
                           year_start=selector.year_start,
                           year_end=selector.year_end,
-                          dry_run=(selector.mode == DRY_RUN),
+                          dry_run=(selector.mode == MODE_DRY_RUN),
                           debug=False)
         if not tool:
             return INLINE_ALERT % (T('Error'), T('Select an harvester.'))
@@ -236,7 +237,7 @@ def insert_marcxml():
                                     selector.id_categories,
                                     year_start=selector.year_start,
                                     year_end=selector.year_end,
-                                    dry_run=(selector.mode == DRY_RUN),
+                                    dry_run=(selector.mode == MODE_DRY_RUN),
                                     debug=False)
         if not tool:
             return INLINE_ALERT % (T('Error'), T('Select an harvester.'))
@@ -290,7 +291,7 @@ def run():
                                     row.harvesters.id_categories,
                                     year_start=selector.year_start,
                                     year_end=selector.year_end,
-                                    dry_run=(selector.mode == DRY_RUN),
+                                    dry_run=(selector.mode == MODE_DRY_RUN),
                                     debug=False)
         if not tool:
             return INLINE_ALERT % (T('Error'), T('Select an harvester.'))
@@ -348,7 +349,7 @@ def run_all():
                                         harvester.id_categories,
                                         year_start=selector.year_start,
                                         year_end=selector.year_end,
-                                        dry_run=(selector.mode == DRY_RUN),
+                                        dry_run=(selector.mode == MODE_DRY_RUN),
                                         debug=False)
             if not tool:
                 return INLINE_ALERT % (T('Error'), T('Select an harvester.'))

controllers/wizards.py

@@ -8,13 +8,13 @@ import re
 from check_tools import check_publication
 from gluon.storage import Storage
 from harvest_tools import DRY_RUN
-from plugin_dbui import (is_foreign_field, 
-                         get_foreign_field, 
-                         Selector, 
+from plugin_dbui import (is_foreign_field,
+                         get_foreign_field,
+                         Selector,
                          to_fields)
 
 
-DRY_RUN = T(DRY_RUN)
+MODE_DRY_RUN = T(DRY_RUN)
 
 INLINE_ALERT = "<script>Ext.Msg.alert('%s', '%s');</script>"
 
@@ -24,31 +24,31 @@ MSG_NO_AUTHORS = "<br><br>Removing affiliation failed.<br>"\
 
 def check_validate():
     """Check and validate publication records.
-    
+
     """
     counters = {}
     logs = []
     id_ok = db(db.status.code=='OK').select().first().id
-    
+
     # get user requirement
     selector = Selector(virtdb.check_selector, exclude_fields=('mode'))
-    
+
     # extract the publication satisfying selector criteria
-    rows = selector.select(db.publications, 
+    rows = selector.select(db.publications,
                            orderby=(db.projects.project, db.categories.code))
-    
+
     # analyse the publications
     for row in rows:
 
-        # alias 
+        # alias
         project = row.projects.project
-        
-        # initialize counters 
+
+        # initialize counters
         if  project not in counters:
-            counters[project] = Storage(found=0, ok=0, validated=0) 
+            counters[project] = Storage(found=0, ok=0, validated=0)
 
         counters[project].found += 1
-        
+
         # skip publication already validated
         if row.status.code == 'OK':
             counters[project].ok += 1
@@ -61,18 +61,18 @@ def check_validate():
         msg.category = row.categories.code
         msg.id = row.publications.id
         msg.project = project
-        msg.title = row.publications.title 
+        msg.title = row.publications.title
         msg.year = row.publications.year
-           
-        # check the record 
+
+        # check the record
         msg.txt, msg.ids = check_publication(row)
-        
+
         # update publication status
-        if not msg.txt: 
+        if not msg.txt:
             counters[project].validated += 1
             del logs[-1]
 
-            if selector.mode != DRY_RUN:
+            if selector.mode != MODE_DRY_RUN:
                 row.publications.update_record(id_status=id_ok)
 
     return dict(counters=counters,
@@ -84,16 +84,16 @@ def check_validate():
 def compare_publications():
     """Compare the publication fields for two ids and show only the difference.
     The arguments of the URL are id1 and id2.
-    
+
     """
     data, idrow = [], []
-    
+
     if 'id1' not in request.vars or 'id2' not in request.vars:
         return INLINE_ALERT % (T('Error'), T('Specify id1 and id2 in the URL'))
-    
+
     row1 = db.publications[request.vars.id1]
     row2 = db.publications[request.vars.id2]
-    
+
     # find the fields of row2 which are different from those of row1
     # the difference is a set containing  (key, value) tuples
     s1 = set(row1.items())
@@ -104,7 +104,7 @@ def compare_publications():
 
         if fieldname in ('delete_record', 'update_record'):
             continue
-        
+
         # alias
         field = db.publications[fieldname]
         value1 = row1[fieldname]
@@ -113,21 +113,21 @@ def compare_publications():
         if fieldname == 'id':
             idrow = ['id', value1, value2]
             continue
-        
+
         # convert foreign fields
         if is_foreign_field(field):
             k_tablename, k_fieldname, k_id = get_foreign_field(field)
-            
+
             value1 = db[k_tablename][value1][k_fieldname]
             value2 = db[k_tablename][value2][k_fieldname]
-            
+
         data.append([T(field.label), value1, value2])
-    
+
     # add the ids as the first data
     # the protection covers the case in which id1=id2
     if idrow:
         data.insert(0, idrow)
-    
+
     # delegate the rendering to the view
     return dict(data=data, title=row1.title)
 
@@ -136,10 +136,10 @@ def extract_authors():
     """Extract a list of authors in a string containing
     author name and their affiliation. It also extract authors for a
     given affiliation.
-    
+
     """
     selector = Selector(virtdb.authors_selector)
-    
+
     # remove stupid character in the authors string
     authors = re.sub(r'[\n\t\r\v\f]', '', selector.authors)
 
@@ -150,19 +150,19 @@ def extract_authors():
     all_authors = []
     my_authors = []
     rex = re.compile('([^\d]+)[ ,]?([\d,a-z\*]+)[ ,]')
-    
+
     for el in rex.finditer(authors):
         author = el.group(1)
-        
+
         # when the matching work, author contains 0 or 1 comma
         # use this property to detect when matching failed
         if author.count(',') > 1:
             case_1 = False
             break
-        
+
         author = author.strip().replace(',', '')
         all_authors.append(author)
-        
+
         if el.group(2) == selector.affiliation:
             my_authors.append(author)
 
@@ -171,21 +171,21 @@ def extract_authors():
 #    if not case_1:
 #        # remove number for footnote
 #        authors = re.sub(r'(,\d)', '', authors)
-#        
+#
 #        # remove space before comma
 #        authors = re.sub(r'( ,)', ',', authors)
-#        
+#
 #        # get author and its affiliation
 #        rex = re.compile(r'([\w \.-]+)[ ]?(a?[a-z],(a?[a-z],)*) ')
 #        for el in rex.finditer(authors):
 #            print el.groups()
-#            
+#
 #        authors = re.sub(r'(a?[a-z],(a?[a-z],)*)', ',', authors)
 #        authors = re.sub(r'[a-z]\Z', '', authors)
-#        
+#
 #        all_authors = authors.split(',')
-            
+
     if not case_1:
         return MSG_NO_AUTHORS
-    
+
     return dict(all=', '.join(all_authors), my_authors=', '.join(my_authors))
\ No newline at end of file

modules/harvest_tools/articles.py

@@ -47,7 +47,7 @@ class Articles(Automaton):
             return False
 
         if self.dbg:
-            print "select article record"
+            print "check article record"
 
         try:
             self.check.clean_erratum(record)

modules/harvest_tools/notes.py

@@ -30,7 +30,7 @@ class Notes(Automaton):
             return False
 
         if self.dbg:
-            print "select note record"
+            print "check note record"
 
         try:
             self.check.submitted(record)

modules/harvest_tools/preprints.py

@@ -36,7 +36,7 @@ class Preprints(Automaton):
             return False
 
         if self.dbg:
-            print "select preprint record"
+            print "check preprint record"
 
         if record.is_published():
             self.logs[-1].reject(MSG_PREPRINT_IS_PAPER, record.year())

modules/harvest_tools/proceedings.py

@@ -30,7 +30,7 @@ class Proceedings(Automaton):
             return False
 
         if self.dbg:
-            print "select and check proceeding record"
+            print "check proceeding record"
 
         try:
             self.check.is_conference(record)

modules/harvest_tools/reports.py

@@ -33,7 +33,7 @@ class Reports(Automaton):
             return False
 
         if self.dbg:
-            print "select report record"
+            print "check report record"
 
         if not record.report_number():
             self.logs[-1].reject(MSG_REPORT_NO_NUMBER, record.year())

modules/harvest_tools/talks.py

@@ -30,7 +30,7 @@ class Talks(Automaton):
             return False
 
         if self.dbg:
-            print "select talk record"
+            print "check talk record"
 
         try:
             self.check.is_conference(record)

modules/harvest_tools/thesis.py

@@ -52,7 +52,7 @@ class Thesis(Automaton):
             return False
 
         if self.dbg:
-            print "select thesis record"
+            print "check thesis record"
 
         if isinstance(record, RecordThesis):
             return True