Merge branch 'cli' into 'master'

Cli

Closes #191

See merge request !4

README.md

@@ -39,16 +39,25 @@ deactivate
 
 ## 2. systems.py
 
-`systems.py` is a script which is intended to be used in the Systems group. Use the `-h` option to see all available parameters. This script allows you to:
+`systems.py` is a script which is intended to be used in the Systems group. Use the `-h` option to see all available parameters.
+To provide input data to the script you can either:  
+- use `--csv` option to use the CSV file
+- or use `-m` (`--documents`) together with `-p` (`--project`) options
 
-1. Print information about input documents on MDMS and GitLab (`-p` is optional):  
-e.g.: `python systems.py -m m55958,m55959,m56121 -p FileFormat/CENC --meeting 133`
-2. Open issues based on the information provided in a CSV file:  
-e.g.: `python systems.py --csv Contribs.csv -o`
+Below are a few examples:
+
+1. Open issues based on the information provided in a CSV file:  
+e.g.: `python systems.py -o --csv Contribs.csv`
+2. Open issues based on CLI options:  
+e.g.: `python systems.py -o -m 55958,55959,56121 -p FileFormat/CENC --meeting 133`
 3. Generate an output document based on the information provided in a CSV file. Use a template as a basis (`--template` is optional):  
-e.g.: `python systems.py --csv Contribs.csv -d --template templates/WG03_input_template_dimitri.docx`
-4. Close issues basd on the information provided in a CSV file:  
-e.g.: `python systems.py --csv Contribs.csv -c`
+e.g.: `python systems.py -d --csv Contribs.csv --template template.docx`
+4. Close issues based on the information provided in a CSV file:  
+e.g.: `python systems.py -c --csv Contribs.csv`
+5. Close issues based on CLI options:  
+e.g.: `python systems.py -c -m m55958,m55959,m56121 -p FileFormat/CENC --meeting 133`
+6. Print information about input documents on MDMS and GitLab:  
+e.g.: `python systems.py -l -m m55958,m55959,m56121 -p FileFormat/CENC --meeting 133`
 
 The CSV file must have a header row with the folowing entries:
 
@@ -56,8 +65,8 @@ The CSV file must have a header row with the folowing entries:
 - To determine which GitLab project needs to be used make sure that your CSV file has either:
   - **Project URL** - a full URL to your GitLab project (*recommended*)
   - or **Sub Group** and **Project Name** - two last elements of the Project URL. (non-case-sensitive)  
-  e.g.: http://mpegx.int-evry.fr/software/MPEG/Systems/PCC-SYS/V-PCC →  `Sub Group = PCC-SYS` and `Project Name = V-PCC`.  
-  e.g.: http://mpegx.int-evry.fr/software/MPEG/Systems/FileFormat/isobmff →  `Sub Group = FileFormat` and `Project Name = ISOBMFF`
+  e.g.: http://mpegx.int-evry.fr/software/MPEG/Systems/PCC-SYS/V-PCC →  `Sub Group=PCC-SYS`, `Project Name=V-PCC`.  
+  e.g.: http://mpegx.int-evry.fr/software/MPEG/Systems/FileFormat/isobmff →  `Sub Group=FileFormat`, `Project Name=ISOBMFF`
 - **Close issue** - is required if you want to close multiple issues at once. Supported values are `0`, `1`, `TRUE`, `FALSE`, `true` and `false`.
 
 The example CSV below has both `Project URL` and (`Sub Group` with `Project Name`) but you can also have one of these in your CSV. The CSV delimiter is determined automatically.

automation/helpers.py

@@ -4,6 +4,7 @@ Some helper functions
 '''
 import json
 import os
+import re
 from datetime import datetime, timedelta
 from docx import Document, opc, oxml, shared
 from docx.enum.text import WD_ALIGN_PARAGRAPH # pylint: disable=E0611
@@ -163,7 +164,7 @@ def find_project(projects, url_or_path, path_root = 'MPEG/'):
   '''
   if url_or_path is None:
     return None
-  striped_url_or_path = url_or_path.replace(' ', '').strip()
+  striped_url_or_path = url_or_path.replace(' ', '').strip().strip('/')
   for project in projects:
     if striped_url_or_path == project['url']:
       return project
@@ -213,7 +214,7 @@ def create_issue_metadata(document, details):
   if len(details['documents']) > 0:
     last_doc = max(details['documents'], key=lambda x:x['version'])
     version = str(last_doc['version'])
-  title = document['title'].replace('(', '').replace(')', '')
+  title = document['title'].replace('(', '').replace(')', '').replace(',', '')
   meta = '[meta]: # ({},{},{},{})'.format(document['mdms_id'], document['document'], title, version)
   return meta
 
@@ -245,7 +246,7 @@ def create_issue_description(document, details):
     description += details['abstract']
   else:
     description += '* [ ] please **add your abstract here**.\n'
-    description += '* [ ] please also **add your abstract to MDMS** (this will be used when we create the output document).\n'
+    description += '* [ ] please also **add your abstract to MDMS** (this can be used when we create the output document).\n'
   description += '\n\n_automatically generated issue_'
   return description
 
@@ -258,4 +259,22 @@ def get_updated_issue_description(current_decription, document, details):
     return None
   description = create_issue_description_header(document, details)
   description += current_decription[pos1+len(CLOSING_TAG):]
-  return description
\ No newline at end of file
+  return description
+
+def find_gitlab_users(gitlab_users, document):
+  usernames = []
+  regex = re.compile(r'[^a-zA-Z\s]')
+  try:
+    for author in document['authors']:
+      author_name = author['name'].lower().strip()
+      author_name = regex.sub('', author_name) # remove non alphabetic chars
+      author_name = ' '.join( [w for w in author_name.split() if len(w)>1] ) # remove single letters
+      for key in gitlab_users:
+        gl_name = gitlab_users[key]['name'].lower().strip()
+        gl_name = regex.sub('', gl_name) # remove non alphabetic chars
+        gl_name = ' '.join( [w for w in gl_name.split() if len(w)>1] ) # remove single letters
+        if author_name == gl_name:
+          usernames.append(key)
+  except:
+    return []
+  return usernames

automation/mdms.py

@@ -4,13 +4,13 @@ This is the interface to MPEG Document Management System (mdms).
 It requests the data from MDMS and parses the output HTML
 '''
 
-from urllib.parse import urljoin, parse_qs, urlparse
 import os
 import requests
 import bs4
+import re
+from urllib.parse import urljoin, parse_qs, urlparse
 from datetime import datetime
 from enum import Enum, unique
-import re
 
 BASE_URL = 'https://dms.mpeg.expert/doc_end_user/'
 MEETINGS_URL = urljoin(BASE_URL, 'all_meeting.php')
@@ -443,4 +443,5 @@ def find_documents( title = '',
   Find documents using the search URL.
   TODO: Fire a POST request to SEARCH_URL and parse the result
   '''
-  return None
\ No newline at end of file
+  return None
+  
\ No newline at end of file