Merge branches 'master' and 'master' of /home/healspersecond/taguette_google_sheet_in...

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

diff --git a/README.md b/README.md
index d3aa877d64dea032f2a0104f8ca9c305d0ded937..0627be07c9cfcc357256820ee40d4a234768f520 100644 (file)
--- a/README.md
+++ b/README.md
@@ -10,10 +10,11 @@ In order to not commit your changes into git, you can run this command:
 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 +53,7 @@ sudo chown taguette:taguette /var/lib/taguette/taguette.sqlite3
 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 --git a/taguette-export_tags_to_csv.py b/taguette-export_tags_to_csv.py
index 8c39554ca87089566564b203dc78dad742dc22f7..d0fd28c4646bb40211cb179eca225d11174df2a3 100755 (executable)
--- a/taguette-export_tags_to_csv.py
+++ b/taguette-export_tags_to_csv.py
@@ -4,51 +4,60 @@ 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')]
 
-## 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 = ""
+    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
+
+            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 = ""
+        
+            # 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])