fix: underscore replace ignore case

sogladev · Mar 4, 2024 · 2226fe4 · 2226fe4
1 parent d5fd9b5
commit 2226fe4
Show file tree

Hide file tree

Showing 4 changed files with 8 additions and 8 deletions.
diff --git a/english/format.ipynb b/english/format.ipynb
@@ -205,7 +205,7 @@
     "    def _replace(e):\n",
     "        if word not in e:\n",
     "           return e \n",
-    "        if not re.match(f\"^{word}.*?$\", e):\n",
+    "        if not re.match(f\"^{word}.*?$\", e, re.IGNORECASE):\n",
     "            return e\n",
     "        return e.replace(word, '_')\n",
     "    example_split_replaced = list(map(lambda e: _replace(e), example_split))\n",
@@ -228,7 +228,7 @@
     "html = style.to_html()\n",
     "filename = DATASET + '_alphabetical'\n",
     "with open(f'output/{filename}.html', 'w') as f:\n",
-    "    f.write(html)\n",
+    "    f.write('<meta charset=\"UTF-8\">'+html)\n",
     "\n",
     "cmd = f'pandoc -f html -t pdf output/{filename}.html -t html5 -o output/{filename}.pdf --metadata pagetitle=\"{filename}\" -V margin-top=2 -V margin-bottom=2 -V margin-left=2 -V margin-right=2 -c format/table.css --pdf-engine-opt=--enable-local-file-access'\n",
     "os.system(cmd)"
@@ -281,7 +281,7 @@
     "html = style.to_html()\n",
     "filename = DATASET + '_underscore_alphabetical'\n",
     "with open(f'output/{filename}.html', 'w') as f:\n",
-    "    f.write(html)\n",
+    "    f.write('<meta charset=\"UTF-8\">'+html)\n",
     "\n",
     "cmd = f'pandoc -f html -t pdf output/{filename}.html -t html5 -o output/{filename}.pdf --metadata pagetitle=\"{filename}\" -V margin-top=2 -V margin-bottom=2 -V margin-left=2 -V margin-right=2 -c format/table.css --pdf-engine-opt=--enable-local-file-access'\n",
     "os.system(cmd)"
@@ -10492,7 +10492,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.10.12"
   },
   "vscode": {
    "interpreter": {

diff --git a/english/format.py b/english/format.py
@@ -32,7 +32,7 @@ def replace_word_in_example_with_underscore(word, example):
     def _replace(e):
         if word not in e:
            return e
-        if not re.match(f"^{word}.*?$", e):
+        if not re.match(f"^{word}.*?$", e, re.IGNORECASE):
             return e
         return e.replace(word, '_')
     example_split_replaced = list(map(lambda e: _replace(e), example_split))
@@ -343,4 +343,4 @@ def fix_latex_line(line):
 #
 ## Run terminal cd format latexmk oxford*.tex to finish build pdfs
 #cmd_build = f"latexmk -pdf -cd format/{DATASET}*.tex -outdir=../output" 
-#os.system(cmd_build)
+#os.system(cmd_build)
diff --git a/spanish/format.ipynb b/spanish/format.ipynb
@@ -265,7 +265,7 @@
     "    def _replace(e):\n",
     "        if word not in e:\n",
     "           return e\n",
-    "        if not re.match(f\"^{word}.*?$\", e):\n",
+    "        if not re.match(f\"^{word}.*?$\", e, re.IGNORECASE):\n",
     "            return e\n",
     "        return e.replace(word, '_')\n",
     "    field_split_replaced = list(map(lambda e: _replace(e), field_split))\n",

diff --git a/spanish/format.py b/spanish/format.py
@@ -29,7 +29,7 @@ def replace_word_in_field_with_underscore(word, field):
     def _replace(e):
         if word not in e:
            return e
-        if not re.match(f"^{word}.*?$", e):
+        if not re.match(f"^{word}.*?$", e, re.IGNORECASE):
             return e
         return e.replace(word, '_')
     field_split_replaced = list(map(lambda e: _replace(e), field_split))