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 cf109db9e776cdbe1d460a9d84ac798c180f9662..d0fd28c4646bb40211cb179eca225d11174df2a3 100755 (executable)
--- a/taguette-export_tags_to_csv.py
+++ b/taguette-export_tags_to_csv.py
@@ -1,12 +1,13 @@
 #!/usr/bin/env python3
 
 import re
+import json
 import sqlite3
 from configparser import ConfigParser
 import csv
 import os
 
-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')]
 
 for file_path in config_files:
 
@@ -27,26 +28,36 @@ for file_path in config_files:
     # Run this if you just want tags and no highlights
     sql_stmt_get = "SELECT id, path, description FROM tags WHERE project_id = ?"
 
-    # 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,))
-
-
+    
     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])
\ No newline at end of file
+            # 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])

diff --git a/taguette-update_tags_from_sheet.py b/taguette-update_tags_from_sheet.py
index 3f550c28df762cd8504c34d7e5b0814e8487e690..565a145fba76d4f9e5fe4a93a3676e0d1d22cb63 100755 (executable)
--- a/taguette-update_tags_from_sheet.py
+++ b/taguette-update_tags_from_sheet.py
@@ -4,6 +4,8 @@ import requests
 from csv import DictReader
 import sqlite3
 from configparser import ConfigParser
+import re
+import json
 
 config = ConfigParser()
 config.read('.taguette_gdocs')
@@ -30,9 +32,11 @@ cur = con.cursor()
 
 for row in DictReader(csv_text.splitlines(), delimiter=","):
     #print(row)
-    tag_id = row['ID']
+    tag_id = row['id']
     new_name = row['tag']
-    axial_code = row['Axial Codes']
+    axial_code = row['axial codes']
+    category = row['category']
+    description = row['description']
 
     sql_stmt_get = "SELECT id, path, description from TAGS where id = ? AND project_id = ?"
     cur.execute(sql_stmt_get, (tag_id, project_id))
@@ -46,21 +50,26 @@ for row in DictReader(csv_text.splitlines(), delimiter=","):
         oldname = tag_info[0][1]
         old_description = tag_info[0][2]
 
-        if row['Axial Codes']:
-            newname = row['Axial Codes'].lower() + "_" + new_name.lower()
+        if axial_code: 
+            newname = axial_code.lower() + "_" + new_name.lower()
         else:
             newname = new_name.lower()
 
+        new_description = description
+        if description and category:
+            new_description += " "
+        if category:
+            new_description += json.dumps({'category' : category})
+
         if not oldname == newname:
-            #print(tag_id)
             sql_stmt_update = "UPDATE tags SET path = ? WHERE project_id = ? AND id = ?"
             cur.execute(sql_stmt_update, (newname, project_id, tag_id))
             print(f"UPDATE TAG: {oldname} → {newname}")
             
-        if row["description"].strip() != old_description.strip():
+        if new_description.strip() != old_description.strip():
             sql_stmt_update = "UPDATE tags SET description = ? WHERE project_id = ? AND id = ?"
-            cur.execute(sql_stmt_update, (row['description'], project_id, tag_id))
-            print(f"UPDATE DESC: {old_description} → {row['description']}")
+            cur.execute(sql_stmt_update, (new_description, project_id, tag_id))
+            print(f"UPDATE DESC: {old_description} → {new_description}")
 
 con.commit()
 con.close()