Built site for gh-pages

.nojekyll

@@ -1 +1 @@
-234bf980
+5acb0938

content/ComparingResults-Options1&2.html

@@ -207,7 +207,7 @@
           <li class="sidebar-item">
   <div class="sidebar-item-container"> 
   <a href="../content/Text_Difference_Checker.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text">difflib Transkribus Output Text Checker</span></a>
+ <span class="menu-text">difflib Transkribus Output Text Checker Notebook</span></a>
   </div>
 </li>
       </ul>

content/Global_Biodiversity_Information_Facility_(GBIF)_API.html

@@ -204,7 +204,7 @@
           <li class="sidebar-item">
   <div class="sidebar-item-container"> 
   <a href="../content/Text_Difference_Checker.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text">difflib Transkribus Output Text Checker</span></a>
+ <span class="menu-text">difflib Transkribus Output Text Checker Notebook</span></a>
   </div>
 </li>
       </ul>

content/Option1.html

@@ -204,7 +204,7 @@
           <li class="sidebar-item">
   <div class="sidebar-item-container"> 
   <a href="../content/Text_Difference_Checker.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text">difflib Transkribus Output Text Checker</span></a>
+ <span class="menu-text">difflib Transkribus Output Text Checker Notebook</span></a>
   </div>
 </li>
       </ul>

content/Option2final.html

@@ -204,7 +204,7 @@
           <li class="sidebar-item">
   <div class="sidebar-item-container"> 
   <a href="../content/Text_Difference_Checker.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text">difflib Transkribus Output Text Checker</span></a>
+ <span class="menu-text">difflib Transkribus Output Text Checker Notebook</span></a>
   </div>
 </li>
       </ul>

content/PyTesseract_OCR.html

@@ -203,7 +203,7 @@
           <li class="sidebar-item">
   <div class="sidebar-item-container"> 
   <a href="../content/Text_Difference_Checker.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text">difflib Transkribus Output Text Checker</span></a>
+ <span class="menu-text">difflib Transkribus Output Text Checker Notebook</span></a>
   </div>
 </li>
       </ul>
@@ -3666,8 +3666,8 @@ <h1>bj170wc5114</h1>
 </script>
 <nav class="page-navigation">
   <div class="nav-page nav-page-previous">
-      <a href="../content/Text_Difference_Checker.html" class="pagination-link" aria-label="difflib Transkribus Output Text Checker">
-        <i class="bi bi-arrow-left-short"></i> <span class="nav-page-text">difflib Transkribus Output Text Checker</span>
+      <a href="../content/Text_Difference_Checker.html" class="pagination-link" aria-label="difflib Transkribus Output Text Checker Notebook">
+        <i class="bi bi-arrow-left-short"></i> <span class="nav-page-text">difflib Transkribus Output Text Checker Notebook</span>
       </a>          
   </div>
   <div class="nav-page nav-page-next">

content/Text_Difference_Checker.html

@@ -117,7 +117,7 @@
       <button type="button" class="quarto-btn-toggle btn" data-bs-toggle="collapse" role="button" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
         <i class="bi bi-layout-text-sidebar-reverse"></i>
       </button>
-        <nav class="quarto-page-breadcrumbs" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item"><a href="../content/image_gallery.html">Text Checker Outputs</a></li><li class="breadcrumb-item"><a href="../content/Text_Difference_Checker.html">difflib Transkribus Output Text Checker</a></li></ol></nav>
+        <nav class="quarto-page-breadcrumbs" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item"><a href="../content/image_gallery.html">Text Checker Outputs</a></li><li class="breadcrumb-item"><a href="../content/Text_Difference_Checker.html">difflib Transkribus Output Text Checker Notebook</a></li></ol></nav>
         <a class="flex-grow-1" role="navigation" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">      
         </a>
       <button type="button" class="btn quarto-search-button" aria-label="Search" onclick="window.quartoOpenSearch();">
@@ -204,7 +204,7 @@
           <li class="sidebar-item">
   <div class="sidebar-item-container"> 
   <a href="../content/Text_Difference_Checker.html" class="sidebar-item-text sidebar-link active">
- <span class="menu-text">difflib Transkribus Output Text Checker</span></a>
+ <span class="menu-text">difflib Transkribus Output Text Checker Notebook</span></a>
   </div>
 </li>
       </ul>

content/experiments-preview.html

@@ -300,7 +300,7 @@ <h6><i class="bi bi-journal-code"></i> experiments</h6>
           <li class="sidebar-item">
   <div class="sidebar-item-container"> 
   <a href="../content/Text_Difference_Checker.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text">difflib Transkribus Output Text Checker</span></a>
+ <span class="menu-text">difflib Transkribus Output Text Checker Notebook</span></a>
   </div>
 </li>
       </ul>

content/experiments.html

@@ -209,7 +209,7 @@
           <li class="sidebar-item">
   <div class="sidebar-item-container"> 
   <a href="../content/Text_Difference_Checker.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text">difflib Transkribus Output Text Checker</span></a>
+ <span class="menu-text">difflib Transkribus Output Text Checker Notebook</span></a>
   </div>
 </li>
       </ul>

content/experiments.out.ipynb

@@ -6,7 +6,7 @@
       "source": [
         "# experiments"
       ],
-      "id": "2dbc8ac2-cbb8-4b0a-abea-79a7b9f48fb3"
+      "id": "bf3cfde9-f8d0-4aad-bbb5-a8bc7a08b2cd"
     },
     {
       "cell_type": "code",
@@ -59,7 +59,7 @@
         "\n",
         "# Results"
       ],
-      "id": "42854845-b54c-412f-9d39-dbda2ae843fb"
+      "id": "26e51538-4c3f-4e3c-bc00-6a03f9c5cbc1"
     },
     {
       "cell_type": "code",
@@ -111,7 +111,7 @@
         "Store, 5. Retrieve (Vector store query). We came up with four main\n",
         "options (below) with some possible variations (see the yellow arrows)."
       ],
-      "id": "03e56a3a-b2f6-494d-b364-7793716d0549"
+      "id": "268a6ec4-c684-4e77-9f97-878591238fb1"
     },
     {
       "cell_type": "code",
@@ -219,7 +219,7 @@
         "}\n",
         "`"
       ],
-      "id": "fc1d0535-2d11-4d5a-9147-70215e67dfe1"
+      "id": "a1678600-c031-4a8a-8ad2-1cba3d6e9bcb"
     },
     {
       "cell_type": "code",
@@ -235,7 +235,7 @@
       "source": [
         "neato = require(\"@observablehq/[email protected]\")"
       ],
-      "id": "ba6830a0-0572-4db4-9182-ffe40a28c6f4"
+      "id": "4094ee4c-68a7-4f5b-a798-24694632520e"
     }
   ],
   "nbformat": 4,

content/image_gallery.html

@@ -170,7 +170,7 @@
           <li class="sidebar-item">
   <div class="sidebar-item-container"> 
   <a href="../content/Text_Difference_Checker.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text">difflib Transkribus Output Text Checker</span></a>
+ <span class="menu-text">difflib Transkribus Output Text Checker Notebook</span></a>
   </div>
 </li>
       </ul>
@@ -230,7 +230,7 @@ <h2 class="anchored" data-anchor-id="motivation-for-checker">Motivation for Chec
 </ul>
 <div class="quarto-figure quarto-figure-center">
 <figure class="figure">
-<p><img src="bv172tc9618/0001_bv172tc9618_0001_diff.jpg" class="img-fluid figure-img"></p>
+<p><img src="bv172tc9618/0001_bv172tc9618_0001_diff.jpg" class="img-fluid figure-img" width="600"></p>
 <figcaption>bv172tc9618_0001</figcaption>
 </figure>
 </div>
@@ -810,8 +810,8 @@ <h2 class="anchored" data-anchor-id="motivation-for-checker">Motivation for Chec
       </a>          
   </div>
   <div class="nav-page nav-page-next">
-      <a href="../content/Text_Difference_Checker.html" class="pagination-link" aria-label="difflib Transkribus Output Text Checker">
-        <span class="nav-page-text">difflib Transkribus Output Text Checker</span> <i class="bi bi-arrow-right-short"></i>
+      <a href="../content/Text_Difference_Checker.html" class="pagination-link" aria-label="difflib Transkribus Output Text Checker Notebook">
+        <span class="nav-page-text">difflib Transkribus Output Text Checker Notebook</span> <i class="bi bi-arrow-right-short"></i>
       </a>
   </div>
 </nav>

content/plan.html

@@ -170,7 +170,7 @@
           <li class="sidebar-item">
   <div class="sidebar-item-container"> 
   <a href="../content/Text_Difference_Checker.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text">difflib Transkribus Output Text Checker</span></a>
+ <span class="menu-text">difflib Transkribus Output Text Checker Notebook</span></a>
   </div>
 </li>
       </ul>

index.html

@@ -169,7 +169,7 @@
           <li class="sidebar-item">
   <div class="sidebar-item-container"> 
   <a href="./content/Text_Difference_Checker.html" class="sidebar-item-text sidebar-link">
- <span class="menu-text">difflib Transkribus Output Text Checker</span></a>
+ <span class="menu-text">difflib Transkribus Output Text Checker Notebook</span></a>
   </div>
 </li>
       </ul>

search.json

@@ -147,7 +147,7 @@
     "text": "Inspiration for this notebook: https://medium.com/@zhangkd5/a-tutorial-for-difflib-a-powerful-python-standard-library-to-compare-textual-sequences-096d52b4c843\n\nfrom difflib import HtmlDiff, SequenceMatcher\n\n# Define the paths to the text files\npath_to_file_a = '0003_bv172tc9618_0003_print.txt'\npath_to_file_b = '0003_bv172tc9618_0003_print.txt'\n\n# Read the contents of the files\nwith open(path_to_file_a, 'r', encoding='utf-8') as file:\n    a = file.read()\n\nwith open(path_to_file_b, 'r', encoding='utf-8') as file:\n    b = file.read()\n\n# Calculate the similarity ratio using SequenceMatcher\nseq_match = SequenceMatcher(None, a, b)\nratio = seq_match.ratio()\n\n# Create the HtmlDiff object\nd = HtmlDiff()\n\n# Generate the HTML diff\nhtml_diff = d.make_file(a.splitlines(), b.splitlines())\n\n# Add the similarity ratio to the HTML diff\nratio_html = f\"<h2>Similarity Ratio: {ratio:.2f}</h2>\\n\" + html_diff\n\n# Save the diff to an HTML file\nwith open('0003_bv172tc9618_0003_print_verify.html', 'w', encoding='utf-8') as f:\n    f.write(ratio_html)\n\n\nScript to read in directories (folders) for each paper\n\nimport os\nfrom difflib import HtmlDiff, SequenceMatcher\n\n# Define the paths to the directories\npath_to_folder_a = './PrintModelText/PrintModelText/zz472cp8582_jpg/txt'\npath_to_folder_b = './PrivateModel_V3/PrivateModel_V3/zz472cp8582_jpg_v3/txt'\n\n# Create the HtmlDiff object\nd = HtmlDiff()\n\n# Get the list of files in each directory\nfiles_a = sorted(os.listdir(path_to_folder_a))\nfiles_b = sorted(os.listdir(path_to_folder_b))\n\n# Ensure both directories have the same number of files\nif len(files_a) != len(files_b):\n    print(\"Error: The directories do not contain the same number of files.\")\n    exit() # exits program is both directories dont have the same number of files\n\n# Compare each pair of files\nfor file_a, file_b in zip(files_a, files_b):\n    # Read the contents of the files\n    with open(os.path.join(path_to_folder_a, file_a), 'r', encoding='utf-8') as fa:\n        a = fa.read()\n    \n    with open(os.path.join(path_to_folder_b, file_b), 'r', encoding='utf-8') as fb:\n        b = fb.read()\n    \n    # Calculate the similarity ratio using SequenceMatcher\n    seq_match = SequenceMatcher(None, a, b)\n    ratio = seq_match.ratio() #calculates the similarity ratios between a & b\n    ratio_percentage = ratio * 100\n    \n    # Generate the HTML diff report on the differences. splitlines() is used to split the content into individual lines\n    html_diff = d.make_file(a.splitlines(), b.splitlines())\n    \n    # Add the similarity ratio to the HTML diff. Ratio is formatted to two decimal places\n    ratio_html = f\"<h2>Similarity Ratio: {ratio_percentage:.2f}%</h2>\\n\" + html_diff\n    \n    # Define the output file name\n    output_file_name = os.path.splitext(file_a)[0] + '_diff.html'\n    \n    # Save the diff to an HTML file\n    with open(output_file_name, 'w', encoding='utf-8') as f:\n        f.write(ratio_html)\n    \n    print(f\"Processed: {output_file_name}\")\n\nprint(\"All files have been processed.\")\n\nProcessed: 0001_zz472cp8582_0001_diff.html\nProcessed: 0002_zz472cp8582_0002_diff.html\nProcessed: 0003_zz472cp8582_0003_diff.html\nProcessed: 0004_zz472cp8582_0004_diff.html\nProcessed: 0005_zz472cp8582_0005_diff.html\nProcessed: 0006_zz472cp8582_0006_diff.html\nProcessed: 0007_zz472cp8582_0007_diff.html\nProcessed: 0008_zz472cp8582_0008_diff.html\nProcessed: 0009_zz472cp8582_0009_diff.html\nProcessed: 0010_zz472cp8582_0010_diff.html\nProcessed: 0011_zz472cp8582_0011_diff.html\nProcessed: 0012_zz472cp8582_0012_diff.html\nProcessed: 0013_zz472cp8582_0013_diff.html\nProcessed: 0014_zz472cp8582_0014_diff.html\nProcessed: 0015_zz472cp8582_0015_diff.html\nProcessed: 0016_zz472cp8582_0016_diff.html\nProcessed: 0017_zz472cp8582_0017_diff.html\nAll files have been processed.\n\n\n\n\nScript to print out Similarity Ratio (%) for each page per paper\n\nimport os\nfrom difflib import HtmlDiff, SequenceMatcher\n\n# Define the paths to the directories\npath_to_folder_a = './PrintModelText/PrintModelText/bv172tc9618_jpg/txt'\npath_to_folder_b = './PrivateModel_V3/PrivateModel_V3/bv172tc9618_jpg_v3/txt'\n\n# Create the HtmlDiff object\nd = HtmlDiff()\n\n# Get the list of files in each directory\nfiles_a = sorted(os.listdir(path_to_folder_a))\nfiles_b = sorted(os.listdir(path_to_folder_b))\n\n# Ensure both directories have the same number of files\nif len(files_a) != len(files_b):\n    print(\"Error: The directories do not contain the same number of files.\")\n    exit()\n\n# Store results for the table\nresults = []\n\n# Compare each pair of files\nfor file_a, file_b in zip(files_a, files_b):\n    # Read the contents of the files\n    with open(os.path.join(path_to_folder_a, file_a), 'r', encoding='utf-8') as fa:\n        a = fa.read()\n    \n    with open(os.path.join(path_to_folder_b, file_b), 'r', encoding='utf-8') as fb:\n        b = fb.read()\n    \n    # Calculate the similarity ratio using SequenceMatcher\n    seq_match = SequenceMatcher(None, a, b)\n    ratio = seq_match.ratio()\n    ratio_percentage = ratio * 100\n    \n    # Generate the HTML diff\n    html_diff = d.make_file(a.splitlines(), b.splitlines())\n    \n    # Add the similarity ratio to the HTML diff\n    ratio_html = f\"<h2>Similarity Ratio: {ratio_percentage:.2f}%</h2>\\n\" + html_diff\n    \n    # Define the output file name\n    output_file_name = os.path.splitext(file_a)[0] + '_comp.html'\n    \n    # Save the diff to an HTML file\n    with open(output_file_name, 'w', encoding='utf-8') as f:\n        f.write(ratio_html)\n    \n    # Print out the processed file\n    print(f\"Processed: {output_file_name}\")\n    \n    # Append the result to the list\n    file_base_name = os.path.splitext(file_a)[0]\n    results.append((file_base_name, ratio_percentage))\n\nprint(\"All files have been processed.\")\n\n# Print out the table\nprint(\"\\nComparison Results:\")\nprint(f\"{'File Name and Page Number':<30} {'Similarity Ratio (%)':<20}\")\nprint(\"=\" * 50)\nfor result in results:\n    print(f\"{result[0]:<30} {result[1]:<20.2f}\")\n\n\nProcessed: 0001_bv172tc9618_0001_comp.html\nProcessed: 0002_bv172tc9618_0002_comp.html\nProcessed: 0003_bv172tc9618_0003_comp.html\nProcessed: 0004_bv172tc9618_0004_comp.html\nProcessed: 0005_bv172tc9618_0005_comp.html\nProcessed: 0006_bv172tc9618_0006_comp.html\nProcessed: 0007_bv172tc9618_0007_comp.html\nProcessed: 0008_bv172tc9618_0008_comp.html\nProcessed: 0009_bv172tc9618_0009_comp.html\nProcessed: 0010_bv172tc9618_0010_comp.html\nProcessed: 0011_bv172tc9618_0011_comp.html\nProcessed: 0012_bv172tc9618_0012_comp.html\nProcessed: 0013_bv172tc9618_0013_comp.html\nProcessed: 0014_bv172tc9618_0014_comp.html\nAll files have been processed.\n\nComparison Results:\nFile Name and Page Number      Similarity Ratio (%)\n==================================================\n0001_bv172tc9618_0001          15.33               \n0002_bv172tc9618_0002          8.80                \n0003_bv172tc9618_0003          19.17               \n0004_bv172tc9618_0004          37.14               \n0005_bv172tc9618_0005          9.09                \n0006_bv172tc9618_0006          39.30               \n0007_bv172tc9618_0007          4.11                \n0008_bv172tc9618_0008          27.47               \n0009_bv172tc9618_0009          3.04                \n0010_bv172tc9618_0010          11.35               \n0011_bv172tc9618_0011          8.27                \n0012_bv172tc9618_0012          50.11               \n0013_bv172tc9618_0013          21.28               \n0014_bv172tc9618_0014          44.60",
     "crumbs": [
       "Text Checker Outputs",
-      "difflib Transkribus Output Text Checker"
+      "difflib Transkribus Output Text Checker Notebook"
     ]
   },
   {