amend

1408e5df · Christian Boulanger · dd068e7b · 1408e5df
Commit 1408e5df authored 7 months ago by Christian Boulanger
--- a/convert-anystyle-data/tei-to-gold.ipynb
+++ b/convert-anystyle-data/tei-to-gold.ipynb
@@ -73,7 +73,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 14,
   "id": "d39d9f75",
   "metadata": {},
   "outputs": [
@@ -90,7 +90,7 @@
       "''"
      ]
     },
-     "execution_count": 9,
+     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -105,7 +105,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 18,
   "id": "2cc1a0d6",
   "metadata": {},
   "outputs": [
@@ -113,7 +113,7 @@
     "data": {
      "text/markdown": [
       "### Processing 10.1111_1467-6478.00057\n",
-       "Files: [TEI/bibl](tei-bibl-corrected/10.1111_1467-6478.00057.xml) | [TEI/biblStruct](tei-biblStruct/10.1111_1467-6478.00057.biblstruct.xml) | [TEI/biblStruct Gold Standard](gold/10.1111_1467-6478.00057.xml)"
+       "Files: [TEI/bibl](tei-bibl-corrected/10.1111_1467-6478.00057.xml) | [TEI/biblStruct](tei-biblStruct/10.1111_1467-6478.00057.biblstruct.xml) | [Gold Standard](gold/10.1111_1467-6478.00057.xml)"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
@@ -123,78 +123,43 @@
     "output_type": "display_data"
    },
    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Unexpected exception formatting exception. Falling back to standard exception\n"
-     ]
+     "data": {
+      "text/markdown": [
+       "### Processing 10.1111_1467-6478.00080\n",
+       "Files: [TEI/bibl](tei-bibl-corrected/10.1111_1467-6478.00080.xml) | [TEI/biblStruct](tei-biblStruct/10.1111_1467-6478.00080.biblstruct.xml) | [Gold Standard](gold/10.1111_1467-6478.00080.xml)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
    },
    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Traceback (most recent call last):\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 3526, in run_code\n",
-      "    exec(code_obj, self.user_global_ns, self.user_ns)\n",
-      "  File \"C:\\Users\\boulanger\\AppData\\Local\\Temp\\ipykernel_23656\\3760719036.py\", line 3, in <module>\n",
-      "    create_all_gold_standards('tei-bibl-corrected',\n",
-      "  File \"c:\\Users\\boulanger\\DataspellProjects\\experiments\\convert-anystyle-data\\lib\\gold_standard.py\", line 223, in create_all_gold_standards\n",
-      "    output_data = create_gold_standard(bibl_content, biblStruct_content, verbose=verbose)\n",
-      "                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\DataspellProjects\\experiments\\convert-anystyle-data\\lib\\gold_standard.py\", line 70, in create_gold_standard\n",
-      "    for parent_element in bibl_tree.xpath(bibl_parent_xpath, namespaces=ns):\n",
-      "                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"src\\\\lxml\\\\etree.pyx\", line 1606, in lxml.etree._Element.xpath\n",
-      "  File \"src\\\\lxml\\\\xpath.pxi\", line 290, in lxml.etree.XPathElementEvaluator.__call__\n",
-      "  File \"src\\\\lxml\\\\xpath.pxi\", line 210, in lxml.etree._XPathEvaluatorBase._handle_result\n",
-      "lxml.etree.XPathEvalError: Invalid expression\n",
-      "\n",
-      "During handling of the above exception, another exception occurred:\n",
-      "\n",
-      "Traceback (most recent call last):\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 2120, in showtraceback\n",
-      "    stb = self.InteractiveTB.structured_traceback(\n",
-      "          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\IPython\\core\\ultratb.py\", line 1435, in structured_traceback\n",
-      "    return FormattedTB.structured_traceback(\n",
-      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\IPython\\core\\ultratb.py\", line 1326, in structured_traceback\n",
-      "    return VerboseTB.structured_traceback(\n",
-      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\IPython\\core\\ultratb.py\", line 1173, in structured_traceback\n",
-      "    formatted_exception = self.format_exception_as_a_whole(etype, evalue, etb, number_of_lines_of_context,\n",
-      "                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\IPython\\core\\ultratb.py\", line 1088, in format_exception_as_a_whole\n",
-      "    frames.append(self.format_record(record))\n",
-      "                  ^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\IPython\\core\\ultratb.py\", line 970, in format_record\n",
-      "    frame_info.lines, Colors, self.has_colors, lvals\n",
-      "    ^^^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\IPython\\core\\ultratb.py\", line 792, in lines\n",
-      "    return self._sd.lines\n",
-      "           ^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\stack_data\\utils.py\", line 145, in cached_property_wrapper\n",
-      "    value = obj.__dict__[self.func.__name__] = self.func(obj)\n",
-      "                                               ^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\stack_data\\core.py\", line 698, in lines\n",
-      "    pieces = self.included_pieces\n",
-      "             ^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\stack_data\\utils.py\", line 145, in cached_property_wrapper\n",
-      "    value = obj.__dict__[self.func.__name__] = self.func(obj)\n",
-      "                                               ^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\stack_data\\core.py\", line 649, in included_pieces\n",
-      "    pos = scope_pieces.index(self.executing_piece)\n",
-      "                             ^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\stack_data\\utils.py\", line 145, in cached_property_wrapper\n",
-      "    value = obj.__dict__[self.func.__name__] = self.func(obj)\n",
-      "                                               ^^^^^^^^^^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\stack_data\\core.py\", line 628, in executing_piece\n",
-      "    return only(\n",
-      "           ^^^^^\n",
-      "  File \"c:\\Users\\boulanger\\AppData\\Local\\miniconda3\\Lib\\site-packages\\executing\\executing.py\", line 164, in only\n",
-      "    raise NotOneValueFound('Expected one value, found 0')\n",
-      "executing.executing.NotOneValueFound: Expected one value, found 0\n"
-     ]
+     "data": {
+      "text/markdown": [
+       "### Processing 10.1515_zfrs-1980-0103\n",
+       "Files: [TEI/bibl](tei-bibl-corrected/10.1515_zfrs-1980-0103.xml) | [TEI/biblStruct](tei-biblStruct/10.1515_zfrs-1980-0103.biblstruct.xml) | [Gold Standard](gold/10.1515_zfrs-1980-0103.xml)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/markdown": [
+       "### Processing 10.1515_zfrs-1980-0104\n",
+       "Files: [TEI/bibl](tei-bibl-corrected/10.1515_zfrs-1980-0104.xml) | [TEI/biblStruct](tei-biblStruct/10.1515_zfrs-1980-0104.biblstruct.xml) | [Gold Standard](gold/10.1515_zfrs-1980-0104.xml)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
    }
   ],
   "source": [

 %% Cell type:markdown id:a7894c78ec06bd10 tags:

 # Translate TEI/bibl to final gold standard schema

 %% Cell type:code id:2a90251a tags:

 ``` python
 %load_ext autoreload
 %autoreload 2
 ```

 %% Output

    The autoreload extension is already loaded. To reload it, use:
      %reload_ext autoreload

 %% Cell type:markdown id:bac6fffc tags:

 Add an `xml:id` attribute to all `bibl` elements so that they can be matched later.

 %% Cell type:code id:338af7ddf4cc739d tags:

 ``` python
 from lib.gold_standard import add_id_to_bibl

 add_id_to_bibl('./tei-bibl-corrected')
 ```

 %% Output

     - Processing ./tei-bibl-corrected\10.1111_1467-6478.00057.xml
     - Processing ./tei-bibl-corrected\10.1111_1467-6478.00080.xml
     - Processing ./tei-bibl-corrected\10.1515_zfrs-1980-0103.xml
     - Processing ./tei-bibl-corrected\10.1515_zfrs-1980-0104.xml

 %% Cell type:markdown id:f18f6515 tags:

 Create `biblStruct` from `bibl`:

 %% Cell type:code id:d39d9f75 tags:

 ``` python
 from lib.xslt import transform
 transform(xslt_path='lib/xslt/convert_tei-to-biblstruct_bibl.xsl',
          input_path='tei-bibl-corrected',
          output_path='tei-biblStruct',
          rename_extension=('-bibl_biblStruct.TEIP5.xml','.biblStruct.xml')).stderr
 ```

 %% Output

    Applied lib\xslt\convert_tei-to-biblstruct_bibl.xsl to files in tei-bibl-corrected and saved result in tei-biblStruct.

    ''

 %% Cell type:code id:2cc1a0d6 tags:

 ``` python
 from lib.gold_standard import create_all_gold_standards

 create_all_gold_standards('tei-bibl-corrected',
                          'tei-biblStruct',
                          'gold',
                          verbose=False)
 ```

 %% Output

    ### Processing 10.1111_1467-6478.00057
-    Files: [TEI/bibl](tei-bibl-corrected/10.1111_1467-6478.00057.xml) | [TEI/biblStruct](tei-biblStruct/10.1111_1467-6478.00057.biblstruct.xml) | [TEI/biblStruct Gold Standard](gold/10.1111_1467-6478.00057.xml)
+    Files: [TEI/bibl](tei-bibl-corrected/10.1111_1467-6478.00057.xml) | [TEI/biblStruct](tei-biblStruct/10.1111_1467-6478.00057.biblstruct.xml) | [Gold Standard](gold/10.1111_1467-6478.00057.xml)

-    Unexpected exception formatting exception. Falling back to standard exception
+    ### Processing 10.1111_1467-6478.00080
+    Files: [TEI/bibl](tei-bibl-corrected/10.1111_1467-6478.00080.xml) | [TEI/biblStruct](tei-biblStruct/10.1111_1467-6478.00080.biblstruct.xml) | [Gold Standard](gold/10.1111_1467-6478.00080.xml)

-    Traceback (most recent call last):
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\IPython\core\interactiveshell.py", line 3526, in run_code
-        exec(code_obj, self.user_global_ns, self.user_ns)
-      File "C:\Users\boulanger\AppData\Local\Temp\ipykernel_23656\3760719036.py", line 3, in <module>
-        create_all_gold_standards('tei-bibl-corrected',
-      File "c:\Users\boulanger\DataspellProjects\experiments\convert-anystyle-data\lib\gold_standard.py", line 223, in create_all_gold_standards
-        output_data = create_gold_standard(bibl_content, biblStruct_content, verbose=verbose)
-                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\DataspellProjects\experiments\convert-anystyle-data\lib\gold_standard.py", line 70, in create_gold_standard
-        for parent_element in bibl_tree.xpath(bibl_parent_xpath, namespaces=ns):
-                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-      File "src\\lxml\\etree.pyx", line 1606, in lxml.etree._Element.xpath
-      File "src\\lxml\\xpath.pxi", line 290, in lxml.etree.XPathElementEvaluator.__call__
-      File "src\\lxml\\xpath.pxi", line 210, in lxml.etree._XPathEvaluatorBase._handle_result
-    lxml.etree.XPathEvalError: Invalid expression
-    
-    During handling of the above exception, another exception occurred:
-    
-    Traceback (most recent call last):
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\IPython\core\interactiveshell.py", line 2120, in showtraceback
-        stb = self.InteractiveTB.structured_traceback(
-              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\IPython\core\ultratb.py", line 1435, in structured_traceback
-        return FormattedTB.structured_traceback(
-               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\IPython\core\ultratb.py", line 1326, in structured_traceback
-        return VerboseTB.structured_traceback(
-               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\IPython\core\ultratb.py", line 1173, in structured_traceback
-        formatted_exception = self.format_exception_as_a_whole(etype, evalue, etb, number_of_lines_of_context,
-                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\IPython\core\ultratb.py", line 1088, in format_exception_as_a_whole
-        frames.append(self.format_record(record))
-                      ^^^^^^^^^^^^^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\IPython\core\ultratb.py", line 970, in format_record
-        frame_info.lines, Colors, self.has_colors, lvals
-        ^^^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\IPython\core\ultratb.py", line 792, in lines
-        return self._sd.lines
-               ^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\stack_data\utils.py", line 145, in cached_property_wrapper
-        value = obj.__dict__[self.func.__name__] = self.func(obj)
-                                                   ^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\stack_data\core.py", line 698, in lines
-        pieces = self.included_pieces
-                 ^^^^^^^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\stack_data\utils.py", line 145, in cached_property_wrapper
-        value = obj.__dict__[self.func.__name__] = self.func(obj)
-                                                   ^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\stack_data\core.py", line 649, in included_pieces
-        pos = scope_pieces.index(self.executing_piece)
-                                 ^^^^^^^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\stack_data\utils.py", line 145, in cached_property_wrapper
-        value = obj.__dict__[self.func.__name__] = self.func(obj)
-                                                   ^^^^^^^^^^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\stack_data\core.py", line 628, in executing_piece
-        return only(
-               ^^^^^
-      File "c:\Users\boulanger\AppData\Local\miniconda3\Lib\site-packages\executing\executing.py", line 164, in only
-        raise NotOneValueFound('Expected one value, found 0')
-    executing.executing.NotOneValueFound: Expected one value, found 0
+    ### Processing 10.1515_zfrs-1980-0103
+    Files: [TEI/bibl](tei-bibl-corrected/10.1515_zfrs-1980-0103.xml) | [TEI/biblStruct](tei-biblStruct/10.1515_zfrs-1980-0103.biblstruct.xml) | [Gold Standard](gold/10.1515_zfrs-1980-0103.xml)
+
+    ### Processing 10.1515_zfrs-1980-0104
+    Files: [TEI/bibl](tei-bibl-corrected/10.1515_zfrs-1980-0104.xml) | [TEI/biblStruct](tei-biblStruct/10.1515_zfrs-1980-0104.biblstruct.xml) | [Gold Standard](gold/10.1515_zfrs-1980-0104.xml)