configure jupyter lite. and update the analysis code, so it works wit…

…h pyodide kernel too.
bitnik · Sep 25, 2024 · eb385e2 · eb385e2
1 parent 789b452
commit eb385e2
Show file tree

Hide file tree

Showing 11 changed files with 17,902 additions and 55 deletions.
diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml
@@ -23,7 +23,7 @@ jobs:
           python -m pip install -r requirements.txt
       - name: Build the JupyterLite site
         run: |
-          jupyter lite build --contents notebooks --output-dir dist
+          jupyter lite build
       - name: Upload artifact
         uses: actions/upload-pages-artifact@v3
         with:

diff --git a/.gitignore b/.gitignore
@@ -161,6 +161,8 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
 
+LOCAL.md
+
 # jupyterlite
 *.doit.db
 _output
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -25,6 +25,12 @@ repos:
   - id: end-of-file-fixer
   - id: trailing-whitespace
   # - id: requirements-txt-fixer
+  - id: check-json
+  - id: pretty-format-json
+    files: ^.*.json$
+    args:
+    - --autofix
+    - --no-sort-keys
 - repo: https://github.com/adrienverge/yamllint.git
   rev: v1.35.1
   hooks:

diff --git a/README.md b/README.md
@@ -43,6 +43,6 @@ Or run JupyterLite server:
 
 ```sh
 # https://jupyterlite.readthedocs.io/en/stable/quickstart/standalone.html
-jupyter lite build --contents notebooks
-jupyter lite serve
+jupyter lite build
+jupyter lite serve --port 8889
 ```
diff --git a/jupyter-lite.json b/jupyter-lite.json
@@ -1,16 +1,13 @@
 {
-    "description": "The jupyter-lite.json file is used to configure the runtime configuration of JupyterLite.",
-    "jupyter-lite-schema-version": 0,
-    "jupyter-config-data": {
-      "appName": "analyse-caesar-cipher",
-      "disabledExtensions": [
-        "@jupyterlab/drawio-extension",
-        "jupyterlab-kernel-spy",
-        "jupyterlab-tour"
-      ],
-      "settingsStorageName": "jupyterlite-analyse-caesar-cipher-storage",
-      "LiteBuildConfig": {
-        "ignore_sys_prefix": ["federated_extensions"]
-      }
-    }
+  "description": "The jupyter-lite.json file is used to configure the runtime configuration of JupyterLite.",
+  "jupyter-lite-schema-version": 0,
+  "jupyter-config-data": {
+    "appName": "analyse-caesar-cipher",
+    "disabledExtensions": [
+      "@jupyterlab/drawio-extension",
+      "jupyterlab-kernel-spy",
+      "jupyterlab-tour"
+    ],
+    "settingsStorageName": "jupyterlite-analyse-caesar-cipher-storage"
   }
+}
diff --git a/jupyter_lite_config.json b/jupyter_lite_config.json
@@ -0,0 +1,9 @@
+{
+  "description": "This file is used to configure the build time configuration of JupyterLite.",
+  "LiteBuildConfig": {
+    "contents": [
+      "notebooks"
+    ],
+    "output_dir": "dist"
+  }
+}
diff --git a/notebooks/analyse_caesar_cipher.ipynb b/notebooks/analyse_caesar_cipher.ipynb
@@ -135,30 +135,20 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from urllib.request import urlopen\n",
-    "\n",
-    "# from collections import Counter\n",
     "import matplotlib.pyplot as plt\n",
     "\n",
-    "# def calculate_letter_frequency(text: str) -> dict:\n",
-    "#     letter_freq: dict = {}\n",
-    "#     text = text.lower()\n",
-    "#     total_count = 0\n",
-    "#     for char in text:\n",
-    "#         if char in ascii_lowercase and char not in letter_freq:\n",
-    "#             letter_freq[char] = text.count(char)\n",
-    "#     return letter_freq\n",
-    "\n",
     "\n",
     "def calculate_letter_frequency(text: str) -> dict:\n",
     "    letter_freq: dict = {}\n",
     "    text = text.lower()\n",
     "    total_count = 0\n",
     "    for char in text:\n",
-    "        if char in ascii_lowercase:\n",
+    "        if char in ALPHABET:\n",
     "            total_count += 1\n",
     "            if char not in letter_freq:\n",
-    "                letter_freq[char] = text.count(char)\n",
+    "                letter_freq[char] = 1\n",
+    "            else:\n",
+    "                letter_freq[char] += 1\n",
     "    for l, f in letter_freq.items():\n",
     "        letter_freq[l] = f * 100 / total_count\n",
     "    return letter_freq\n",
@@ -173,22 +163,27 @@
     "    plt.xlabel(\"Characters\")\n",
     "    plt.ylabel(\"Frequency %\")\n",
     "    plt.title(title)\n",
-    "    plt.show()\n",
-    "\n",
-    "\n",
-    "url_hamlet = \"https://www.gutenberg.org/cache/epub/1787/pg1787.txt\"\n",
-    "with urlopen(url_hamlet) as f:\n",
-    "    text = f.read().decode(\"utf-8\").strip()\n",
-    "    # print(Counter(text))\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d2b74dcd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Exmaples with example data\n",
+    "with open(\"./data/hamlet.txt\") as f:\n",
+    "    text = f.read().strip()\n",
     "    letter_freq = calculate_letter_frequency(text)\n",
-    "    print(letter_freq)\n",
+    "    # print(letter_freq)\n",
     "    plot_histogram(letter_freq)\n",
     "\n",
-    "url_romeo_and_juliet = \"https://www.gutenberg.org/cache/epub/47960/pg47960.txt\"\n",
-    "with urlopen(url_romeo_and_juliet) as f:\n",
-    "    text = f.read().decode(\"utf-8\").strip()\n",
+    "with open(\"./data/romeo_and_juliet.txt\") as f:\n",
+    "    text = f.read().strip()\n",
     "    letter_freq = calculate_letter_frequency(text)\n",
-    "    print(letter_freq)\n",
+    "    # print(letter_freq)\n",
     "    plot_histogram(letter_freq)"
    ]
   },
@@ -284,24 +279,45 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "058099ed-d266-4ce1-80b1-17371492bedd",
+   "id": "ed08ebd7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import HTML, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3e8ee124",
    "metadata": {},
    "outputs": [],
    "source": [
     "# Ex: Brvruja rmnjb jan dbnm rw vxmnaw mjcj-lxvyanbbrxw cnlqwrzdnb bdlq jb Qdoovjw lxmrwp.\n",
     "# https://cryptii.com/pipes/caesar-cipher\n",
-    "print(\"\")\n",
-    "example_encrypted_text = input(\"Give me a cipher text to break:\")\n",
-    "print(\"\")\n",
     "\n",
+    "display(HTML(f\"<strong>Give me a cipher text to break</strong>: \"))\n",
+    "example_encrypted_text = input(\"\")\n",
+    "\n",
+    "# Workaround for Pyodide kernel, its `input` function returns PyodideFuture object.\n",
+    "if type(example_encrypted_text) != str:\n",
+    "    example_encrypted_text = await example_encrypted_text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "058099ed-d266-4ce1-80b1-17371492bedd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "letter_freq = calculate_letter_frequency(example_encrypted_text)\n",
     "plot_histogram(letter_freq, title=\"Frequency analysis of given encrypted text\")\n",
     "plot_histogram(LETTER_FREQUENCY, title=\"Frequency analysis of English alphabet\")\n",
     "\n",
     "encryption_key = break_cipher(example_encrypted_text)\n",
-    "print(\"\")\n",
     "decrypted_text = decrypt(example_encrypted_text, encryption_key)\n",
-    "print(f\"Decrypted text: {decrypted_text}\")"
+    "display(HTML(f\"<br><strong>Decrypted text</strong>: {decrypted_text}\"))"
    ]
   },
   {
@@ -320,19 +336,20 @@
    "outputs": [],
    "source": [
     "# example = \"My name is John.\"\n",
-    "# print(example)\n",
+    "# print(f\"Plain text: {example}\")\n",
     "# letter_freq = calculate_letter_frequency(example)\n",
     "# plot_histogram(letter_freq)\n",
     "\n",
     "# encrypted_text = encrypt(example, 9)\n",
-    "# print(encrypted_text)\n",
+    "# print(f\"Encrypted text: {encrypted_text}\")\n",
     "# letter_freq = calculate_letter_frequency(encrypted_text)\n",
     "# plot_histogram(letter_freq)\n",
     "\n",
     "# encryption_key = break_cipher(encrypted_text)\n",
-    "# print(encryption_key)\n",
+    "# print(f\"Encryption key: {encryption_key}\")\n",
     "\n",
-    "# decrypt(encrypted_text, encryption_key)"
+    "# decrypted_text = decrypt(encrypted_text, encryption_key)\n",
+    "# display(HTML(f\"<br><strong>Decrypted text</strong>: {decrypted_text}\"))"
    ]
   },
   {
@@ -346,8 +363,9 @@
     "# # If he had anything confidential to say, he wrote it in cipher, that is, by so changing the order of the letters of the alphabet, that not a word could be made out.\n",
     "# example = \"Vs ur unq nalguvat pbasvqragvny gb fnl, ur jebgr vg va pvcure, gung vf, ol fb punatvat gur beqre bs gur yrggref bs gur nycunorg, gung abg n jbeq pbhyq or znqr bhg.\"\n",
     "# encryption_key = break_cipher(example)\n",
-    "# print(encryption_key)\n",
-    "# decrypt(example, encryption_key)"
+    "# print(f\"Encryption key: {encryption_key}\")\n",
+    "# decrypted_text = decrypt(example, encryption_key)\n",
+    "# display(HTML(f\"<br><strong>Decrypted text</strong>: {decrypted_text}\"))"
    ]
   },
   {

diff --git a/notebooks/data/README.md b/notebooks/data/README.md
@@ -0,0 +1,4 @@
+```sh
+wget https://www.gutenberg.org/cache/epub/1787/pg1787.txt -O hamlet.txt
+wget https://www.gutenberg.org/cache/epub/47960/pg47960.txt -O romeo_and_juliet.txt
+```