From: Benjamin Mako Hill <mako@atdot.cc>
Date: Tue, 28 Feb 2023 00:54:38 +0000 (-0800)
Subject: Merge branches 'master' and 'master' of /home/healspersecond/taguette_google_sheet_in... 
X-Git-Url: https://code.communitydata.science/taguette_google_sheet_integration.git/commitdiff_plain/6926d9d22320e3ae1247fe11ab1e2ba83680232b

Merge branches 'master' and 'master' of /home/healspersecond/taguette_google_sheet_integration

fix some bugs and integrate the changes from the branches from charlie and mako
---

6926d9d22320e3ae1247fe11ab1e2ba83680232b
diff --cc README.md
index d3aa877,d3aa877..0627be0
--- a/README.md
+++ b/README.md
@@@ -10,10 -10,10 +10,11 @@@ In order to not commit your changes int
  git update-index --assume-unchanged .taguette_gdocs
  ```
  
--I also create a directory called `taguette_backups` like:
++I also create a directory called `taguette_backups` and one called `exported_tags` like:
  
  ```
  mkdir taguette_backups
++mkdir exported_tags
  ```
  
  ## Step 1: Backing things up
@@@ -52,7 -52,7 +53,7 @@@ sudo chown taguette:taguette /var/lib/t
  Exporting tags should be as easy as:
  
  ```
--python3 taguette-export_tags_to_csv.py > exported_tags.tsv
++python3 taguette-export_tags_to_csv.py
  ```
  
  This will create a new file called `exported_tags.tsv` which you can manually
diff --cc taguette-export_tags_to_csv.py
index 8c39554,cf109db..d0fd28c
--- a/taguette-export_tags_to_csv.py
+++ b/taguette-export_tags_to_csv.py
@@@ -1,54 -1,52 +1,63 @@@
  #!/usr/bin/env python3
  
  import re
 +import json
  import sqlite3
  from configparser import ConfigParser
+ import csv
+ import os
  
- config = ConfigParser()
- config.read('.taguette_gdocs')
 -config_files = [f for f in os.listdir() if f.startswith('.taguette_gdocs_')]
++config_files = [f for f in os.listdir() if f.startswith('.taguette_gdocs')]
  
- ## this is project ID from the configuration
- project_id = int(config['General']['taguette_project_id'])
- taguette_database_file = config['General']['taguette_database_file']
+ for file_path in config_files:
  
+     config = ConfigParser()
+     config.read(file_path)
  
- ## connect to sqlite3
- con = sqlite3.connect(taguette_database_file)
- cur = con.cursor()
+     ## this is project ID from the configuration
+     project_id = int(config['General']['taguette_project_id'])
+     taguette_database_file = config['General']['taguette_database_file']
  
- # Run this if you just want tags and no highlights
- sql_stmt_get = "SELECT id, path, description FROM tags WHERE project_id = ?"
+     # set output file name
+     output_file_name = f'exported_tags/exported_tags_{project_id}.tsv'
  
- # Run this if you want tags AND highlights
- #sql_stmt_get = "SELECT tags.id, tags.path, tags.description, highlights.snippet FROM highlight_tags INNER JOIN tags ON highlight_tags.tag_id = tags.id INNER JOIN highlights ON highlight_tags.highlight_id = highlights.id WHERE project_id = ?"
- cur.execute(sql_stmt_get, (project_id,))
+     ## connect to sqlite3
+     con = sqlite3.connect(taguette_database_file)
+     cur = con.cursor()
  
- # print out a header
- print("\t".join(['id', 'axial codes', 'tags', 'category', 'description']))
+     # Run this if you just want tags and no highlights
+     sql_stmt_get = "SELECT id, path, description FROM tags WHERE project_id = ?"
  
- while True:
-     row = cur.fetchone()
-     if row == None:
-         break
-         
-     tag_id, path, description = row
- 
-     tag_match = re.match(r'^(.+)\_(.*)$', path) 
-     if tag_match:
-         axial = tag_match.group(1)
-         tag = tag_match.group(2)
-     else:
-         axial = ""
-         tag = path
- 
-     # look for extra category information stored in the description
-     cat_match = re.match('^(.*)\s*(\{(.*)\})$', description)
-     if cat_match:
-         description = cat_match.group(1)
-         category = json.loads(cat_match.group(2))["category"]
-     else:
-         category = ""
 -    # Run this if you want tags AND highlights
 -    #sql_stmt_get = "SELECT tags.id, tags.path, tags.description, highlights.snippet FROM highlight_tags INNER JOIN tags ON highlight_tags.tag_id = tags.id INNER JOIN highlights ON highlight_tags.highlight_id = highlights.id WHERE project_id = ?"
+     cur.execute(sql_stmt_get, (project_id,))
 -
 -
 +    
-     print("\t".join([str(tag_id), axial, tag, category, description]))
+     with open(output_file_name, 'w', newline='') as output_file:
+         writer = csv.writer(output_file, delimiter='\t')
++        writer.writerow(['id', 'axial codes', 'tag', 'category', 'description', 'url'])
++
+         while True:
+             row = cur.fetchone()
+             if row == None:
+                 break
 -
++                
+             tag_id, path, description = row
+ 
 -            m = re.match(r'^(.+)\_(.*)$', path)
 -            if m:
 -                axial = m.group(1)
 -                tag = m.group(2)
++            tag_match = re.match(r'^(.+)\_(.*)$', path) 
++            if tag_match:
++                axial = tag_match.group(1)
++                tag = tag_match.group(2)
+             else:
+                 axial = ""
+                 tag = path
+ 
 -            writer.writerow([str(tag_id), axial, tag, description])
++            # look for extra category information stored in the description
++            cat_match = re.match('^(.*)\s*(\{(.*)\})$', description)
++            if cat_match:
++                description = cat_match.group(1)
++                category = json.loads(cat_match.group(2))["category"]
++            else:
++                category = ""
++        
++            # create a URL that will link to the list of highlights
++            url = f"https://taguette.communitydata.science/project/{project_id}/highlights/{tag}"
 +
++            writer.writerow([str(tag_id), axial, tag, category, description, url])