add filename validation

sanger-tol · Aug 18, 2023 · 6eb7f13 · 6eb7f13
1 parent 5946725
commit 6eb7f13
Show file tree

Hide file tree

Showing 2 changed files with 32 additions and 3 deletions.
diff --git a/work/validate_bioscan.ipynb b/work/validate_bioscan.ipynb
@@ -53,7 +53,8 @@
     "\n",
     "    # orange cols\n",
     "    validate_regex('CATCH_LOT', df, na_values=[])\n",
-    "    df, gal = validate_plates_wells(df, contrib_df, 'RACK_OR_PLATE_ID', 'TUBE_OR_WELL_ID', bioscan=True)\n",
+    "    df, gal, partner_code = validate_plates_wells(\n",
+    "        df, contrib_df, 'RACK_OR_PLATE_ID', 'TUBE_OR_WELL_ID', bioscan=True)\n",
     "    # check and exclude blanks\n",
     "    is_blank = check_blanks(df)\n",
     "    if df[~is_blank].shape[0] == 0:\n",
@@ -106,6 +107,7 @@
     "    validate_freetext('OTHER_INFORMATION', df)\n",
     "    validate_freetext('MISC_METADATA', df)\n",
     "    validate_identifier('IDENTIFIED_BY', df, contrib_df, na_values=[''])\n",
+    "    validate_input_filename(fn, partner_code, v)\n",
     "    \n",
     "    df = expand_plate_only(df)\n",
     "    df = add_sts_cols(df, contrib_df, gal, bioscan=True, v=v)\n",
@@ -166,7 +168,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9259b231",
+   "id": "5ae435ce",
    "metadata": {},
    "outputs": [],
    "source": []

diff --git a/work/validate_partner_manifest_dev.ipynb b/work/validate_partner_manifest_dev.ipynb
@@ -489,6 +489,7 @@
     "    else:\n",
     "        # anospp\n",
     "        unknown_prefixes = (~plate_prefixes.isin(contrib_df['PARTNER_CODE']))\n",
+    "        selected_partner_code = 'SANG'\n",
     "        gal = \"Sanger Institute\"\n",
     "    if unknown_prefixes.any():\n",
     "        logging.error(f'plate ID prefixes not recognised for {plates[unknown_prefixes].to_list()}')\n",
@@ -532,7 +533,7 @@
     "    logging.info(f'{df.shape[0]} samples found across {df[plate_col].nunique()} plates')\n",
     "    \n",
     "\n",
-    "    return df, gal\n",
+    "    return df, gal, selected_partner_code\n",
     "        \n",
     "# df = validate_plates_wells(df, contrib_df, 'RACK_OR_PLATE_ID', 'TUBE_OR_WELL_ID')"
    ]
@@ -1144,6 +1145,25 @@
     "# validate_freetext('IDENTIFIED_HOW', df)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def validate_input_filename(input_fn, partner_code, bioscan_version):\n",
+    "    \n",
+    "    # ABCD_YYMM_\n",
+    "    v = bioscan_version.strip('v')\n",
+    "    fn_regex = f'^{partner_code}_(2[0-3])(0[1-9]|1[0-2])_BIOSCAN_Manifest_V{v}.*xlsx$'\n",
+    "    \n",
+    "    fn_basename = os.path.basename(input_fn)\n",
+    "    \n",
+    "    if not re.match(fn_regex, fn_basename):\n",
+    "        logging.warning(f'input filename {fn_basename} does not match '\n",
+    "                        f'{partner_code}_YYMM_BIOSCAN_Manifest_V{v}*xlsx')"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -1195,6 +1215,13 @@
     "# add_sts_cols(df, contrib_df, gal='Sanger Institute');"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "code",
    "execution_count": null,