mirror of
https://github.com/ckaczor/azuredatastudio.git
synced 2026-01-15 17:22:25 -05:00
440 lines
25 KiB
Plaintext
440 lines
25 KiB
Plaintext
{
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"name": "python3",
|
|
"display_name": "Python 3"
|
|
},
|
|
"language_info": {
|
|
"name": "python",
|
|
"version": "3.6.6",
|
|
"mimetype": "text/x-python",
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"pygments_lexer": "ipython3",
|
|
"nbconvert_exporter": "python",
|
|
"file_extension": ".py"
|
|
}
|
|
},
|
|
"nbformat_minor": 2,
|
|
"nbformat": 4,
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"# Create Jupyter Book\n",
|
|
" <span style=\"color:red\">**Note**:</span> **Windows users** using **Python 3.8** might be impacted by this known [issue](https://jupyterbook.org/advanced/advanced.html#working-on-windows) on the latest **jupyter book** version.\n",
|
|
"\n",
|
|
" <span style=\"color:red\">**Note**:</span> In Jupyter Book versions above 0.7.0, verify that the names of the files do not start with a **number**. Due to the new design of jupyter book, the prefix number will be removed from the file name in the Table of Contents. Please refer to this [section](https://jupyterbook.org/customize/toc.html#automatically-generate-your-toc-yml-file) of the documentation for more information.\n",
|
|
"\n",
|
|
"\n",
|
|
"This is a notebook to create a [Jupyter Book](https://jupyterbook.org/intro.html), which is an organized collections of Jupyter notebooks.\n",
|
|
"\n",
|
|
"The best way to use this notebook is by clicking Run all in the toolbar above. This will run all the cells in a step-by-step order so that you can create your Jupyter Book.\n",
|
|
"\n",
|
|
" \n",
|
|
"## 1. Installation\n",
|
|
"\n",
|
|
"To install the Jupyter Book command-line interface (CLI), use `pip`!"
|
|
],
|
|
"metadata": {
|
|
"azdata_cell_guid": "97541c75-b1c9-4e4c-9f0a-f93df4a550ef"
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": [
|
|
"import sys\n",
|
|
"\n",
|
|
"def getJupyterBookVersion():\n",
|
|
" cmd = f'{sys.executable} -m pip show jupyter-book'\n",
|
|
" cmdOutput = !{cmd}\n",
|
|
" if len(cmdOutput) <= 1:\n",
|
|
" cmd = f'{sys.executable} -m pip install jupyter-book'\n",
|
|
" !{cmd}\n",
|
|
" cmd = f'{sys.executable} -m pip show jupyter-book'\n",
|
|
" cmdOutput = !{cmd}\n",
|
|
" for x in cmdOutput:\n",
|
|
" if 'version' in x.lower():\n",
|
|
" version_str = tuple(x.split(': ')[1].replace('.', ''))\n",
|
|
" version = tuple(int(x) for x in version_str)\n",
|
|
" return version, version_str"
|
|
],
|
|
"metadata": {
|
|
"azdata_cell_guid": "4bc12e83-cd03-425b-ad82-3ea9e0393b2c",
|
|
"tags": [
|
|
"hide_input"
|
|
]
|
|
},
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": [
|
|
"import sys\r\n",
|
|
"\r\n",
|
|
"try:\r\n",
|
|
" version, version_str = getJupyterBookVersion()\r\n",
|
|
" if version:\r\n",
|
|
" display_version = '.'.join(version_str)\r\n",
|
|
" print(f'Jupyter-book version {display_version} is already installed!')\r\n",
|
|
" use_current = input(f'Would you like to create a book using the current installed version [{display_version}] of jupyter-book? [y/n]').lower()\r\n",
|
|
"\r\n",
|
|
" while use_current not in ['','yes', 'y', 'no', 'n']:\r\n",
|
|
" use_current = input(f'Would you like to create a book using the current installed version [{display_version}] of jupyter-book? [y/n]').lower()\r\n",
|
|
" if use_current in ['no', 'n']:\r\n",
|
|
" install_version = input(f'Please enter the version you would like to use (eg. 0.7.4)')\r\n",
|
|
" if install_version:\r\n",
|
|
" cmd = f'{sys.executable} -m pip uninstall jupyter-book --yes'\r\n",
|
|
" !{cmd}\r\n",
|
|
" version = ''\r\n",
|
|
" print('Installing Jupyter-book...')\r\n",
|
|
" cmd = f'{sys.executable} -m pip install jupyter-book=={install_version}'\r\n",
|
|
" !{cmd}\r\n",
|
|
" version, _ = getJupyterBookVersion()\r\n",
|
|
"except Exception as e:\r\n",
|
|
" raise SystemExit(str(e))"
|
|
],
|
|
"metadata": {
|
|
"azdata_cell_guid": "8bd77173-2f63-4bf8-95e8-af2a654fc91e",
|
|
"tags": [
|
|
"hide_input"
|
|
]
|
|
},
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## 2. Create a new book\r\n",
|
|
"\r\n",
|
|
"Create a book using your own notebooks and markdown pages:\r\n",
|
|
"\r\n",
|
|
"<span style=\"color:red\">Note:</span> Notebook and markdown filenames cannot contain spaces"
|
|
],
|
|
"metadata": {
|
|
"azdata_cell_guid": "6a1b6bb8-9cb8-43d5-878f-2029d1eacb0e"
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": [
|
|
"import os, re, subprocess\r\n",
|
|
"from sys import platform\r\n",
|
|
"import shutil\r\n",
|
|
"\r\n",
|
|
"os.environ[\"LC_ALL\"]=\"en_US.UTF-8\"\r\n",
|
|
"\r\n",
|
|
"try:\r\n",
|
|
" overwrite = False\r\n",
|
|
" book_name = input('Please provide the path where the book needs to be saved along with the book name ex-> D:\\Book1: ') \r\n",
|
|
"\r\n",
|
|
" if (os.path.exists(book_name)):\r\n",
|
|
" new_book_name = input('A folder named ' + book_name + ' already exists. Enter a new name or the same name to overwrite the existing folder.\\n')\r\n",
|
|
" if book_name == new_book_name:\r\n",
|
|
" overwrite = True\r\n",
|
|
" book_name = new_book_name\r\n",
|
|
"\r\n",
|
|
" content_folder = input('Please provide the path to your folder containing notebooks and markdown files: ')\r\n",
|
|
"\r\n",
|
|
" while (not os.path.exists(content_folder)):\r\n",
|
|
" content_folder = input('Cannot find folder ' + content_folder + '. Please provide another path: ')\r\n",
|
|
" if version and version < (0,7,0):\r\n",
|
|
" if overwrite:\r\n",
|
|
" !jupyter-book create \"$book_name\" --content-folder \"$content_folder\" --overwrite\r\n",
|
|
" else:\r\n",
|
|
" !jupyter-book create \"$book_name\" --content-folder \"$content_folder\"\r\n",
|
|
" elif version:\r\n",
|
|
" if overwrite:\r\n",
|
|
" shutil.rmtree(book_name)\r\n",
|
|
" # waiting for shutil to remove the directory\r\n",
|
|
" while os.path.exists(book_name):\r\n",
|
|
" pass\r\n",
|
|
" os.mkdir(book_name)\r\n",
|
|
" content_folder = os.path.join(content_folder,'')\r\n",
|
|
" if platform in ['linux', 'darwin']:\r\n",
|
|
" subprocess.check_call(['cp', '-r',content_folder, book_name])\r\n",
|
|
" else:\r\n",
|
|
" subprocess.check_call(['xcopy', content_folder, book_name, '/E', '/H'])\r\n",
|
|
" !jupyter-book toc \"$book_name\"\r\n",
|
|
"except Exception as e:\r\n",
|
|
" raise SystemExit(str(e))"
|
|
],
|
|
"metadata": {
|
|
"azdata_cell_guid": "d1a363f0-d854-4466-be87-d01d4c7e51ef",
|
|
"tags": [
|
|
"hide_input"
|
|
]
|
|
},
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## 3. Format toc.yml file of the book\r\n",
|
|
"\r\n",
|
|
"Create a valid toc.yml file that enables your book to be opened on our viewlet.\r\n",
|
|
"\r\n",
|
|
"<span style=\"color:red\">Note:</span> Skipping this step may result in a malformed book being generated."
|
|
],
|
|
"metadata": {
|
|
"azdata_cell_guid": "5a29e2dd-d9f5-4dc1-87bc-bce639362f51"
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": [
|
|
"# Update toc file, book title and clean up the directores\n",
|
|
"import shutil\n",
|
|
"from os import path\n",
|
|
"import yaml\n",
|
|
"def getMarkdownFile(url):\n",
|
|
" # url are usually defined in toc as: \"- url: <Path\\to\\notebookFile>\"\n",
|
|
" # substring from 7th postion excluding the \"- url: \" from the path\n",
|
|
" #folders = url[7:].rstrip().split(path.sep)\n",
|
|
" if (os.name == 'nt'):\n",
|
|
" # if windows get the drive letter and add it to the url\n",
|
|
" driveletter = content_folder.split(path.sep)[0]\n",
|
|
" markdownFilePath = path.join(driveletter, url[7:].rstrip()+'.md')\n",
|
|
" else:\n",
|
|
" markdownFilePath = url[7:].rstrip() + '.md'\n",
|
|
" return markdownFilePath\n",
|
|
"\n",
|
|
"def getAllSections(visited, data, current):\n",
|
|
" if current not in visited:\n",
|
|
" visited.append(current)\n",
|
|
" for x in range(len(current)):\n",
|
|
" if 'sections' in current[x].keys():\n",
|
|
" tmp = {}\n",
|
|
" tmp['title'] = path.dirname(current[x]['file']).title()\n",
|
|
" tmp['file'] = current[x]['file']\n",
|
|
" tmp['numbered'] = False\n",
|
|
" tmp['expand_sections'] = True\n",
|
|
" tmp['sections'] = current[x]['sections']\n",
|
|
" current[x] = tmp\n",
|
|
" getAllSections(visited, data, current[x]['sections'])\n",
|
|
" else:\n",
|
|
" current[x]['title'] = path.basename(current[x]['file']).title()\n",
|
|
"\n",
|
|
"if version < (0,7,0):\n",
|
|
" tocFilePath = path.join(book_name, \"_data\", \"toc.yml\")\n",
|
|
" f = open(tocFilePath, \"r\")\n",
|
|
" title = ''\n",
|
|
" replacedString = ''\n",
|
|
" result = f.read()\n",
|
|
" f.close()\n",
|
|
" contentFolders = []\n",
|
|
"\n",
|
|
" firstLevelUrls = re.findall(r'^(?:\\s+$[\\r\\n]+)+(\\- url: [a-zA-Z0-9\\\\.\\s\\-\\/]+$[\\r\\n]+)', result, re.MULTILINE)\n",
|
|
" urls = re.findall(r'- url: [a-zA-Z0-9\\\\.\\s\\-\\/]+$', result, re.MULTILINE)\n",
|
|
" headers = re.findall(r'- header: [a-zA-Z0-9\\\\.\\s-]+$', result, re.MULTILINE)\n",
|
|
" # all the markdown urls are placed at the end of the list. \n",
|
|
" possibleMarkdowns = re.findall(r'(- url: [a-zA-Z0-9\\\\.\\s\\-\\/]+$[\\r\\n]+)[\\r\\n]', result, re.MULTILINE)\n",
|
|
"\n",
|
|
" try:\n",
|
|
" if (firstLevelUrls or headers or urls):\n",
|
|
" if (firstLevelUrls and len(firstLevelUrls) == 1):\n",
|
|
" for url in firstLevelUrls:\n",
|
|
" # check first link is the markdown\n",
|
|
" title = url[url.rindex(path.sep)+1:].rstrip()\n",
|
|
" markdownFilePath = getMarkdownFile(url)\n",
|
|
" rootmarkdownExists = path.exists(markdownFilePath)\n",
|
|
" markdownUrl = urls[len(urls) -1]\n",
|
|
" if (rootmarkdownExists):\n",
|
|
" markdownUrl = url\n",
|
|
" replacedString = \"\\n- title: %s\\n url: /%s\\n not_numbered: true\\n\" % (title, title)\n",
|
|
" # else check if the last link in the url list is markdown \n",
|
|
" elif (not headers and path.exists(getMarkdownFile(markdownUrl))):\n",
|
|
" rootmarkdownExists = True\n",
|
|
" title = markdownUrl[markdownUrl.rindex(path.sep)+1:].rstrip()\n",
|
|
" replacedString = \"\\n- title: %s\\n url: /%s\\n not_numbered: true\\n expand_sections: true\\n sections: %s\" % (title, title, url)\n",
|
|
" result = result.replace(markdownUrl, '')\n",
|
|
" # if there not markdowns and folders contains markdowns, handle them\n",
|
|
" elif (possibleMarkdowns):\n",
|
|
" markdownUrl = possibleMarkdowns[0]\n",
|
|
" title = markdownUrl[markdownUrl.rindex(path.sep)+1:].rstrip()\n",
|
|
" markdownFilePath = getMarkdownFile(markdownUrl)\n",
|
|
" rootmarkdownExists = path.exists(markdownFilePath)\n",
|
|
" if (rootmarkdownExists):\n",
|
|
" replacedString = \"\\n- title: %s\\n url: /%s\\n not_numbered: true\\n expand_sections: true\\n sections: %s\" % (title, title, url)\n",
|
|
" result = result.replace(markdownUrl, '')\n",
|
|
" # there is no markdown and we're adding the first link as is\n",
|
|
" else:\n",
|
|
" markdownUrl = url\n",
|
|
" replacedString = \"\\n- title: %s\\n url: /%s\\n not_numbered: true\\n\" % (title, title)\n",
|
|
" result = result.replace(url, replacedString)\n",
|
|
" # Folders and handling them -> each header is a folder\n",
|
|
" if (headers):\n",
|
|
" for header in headers:\n",
|
|
" title = header[10:].rstrip()\n",
|
|
" # filters all the urls with /headerName in them\n",
|
|
" filtered = list(filter(lambda x: (\"%s%s%s\" % (path.sep, title.lower(), path.sep)) in x.lower(), urls))\n",
|
|
" index = urls.index(filtered[len(filtered)-1])\n",
|
|
" markdownFilePath = getMarkdownFile(filtered[len(filtered)-1])\n",
|
|
" markdownExists = path.exists(markdownFilePath)\n",
|
|
" if (not markdownExists):\n",
|
|
" index = urls.index(filtered[0])\n",
|
|
" folderEndIndex = urls[index].rindex(path.sep)\n",
|
|
" caseSensitiveFolderName = urls[index][urls[index].rindex(path.sep, 0, folderEndIndex)+1:folderEndIndex]\n",
|
|
" contentFolders.append(caseSensitiveFolderName)\n",
|
|
" urlValue = urls[index][urls[index].rindex(path.sep)+1:].rstrip()\n",
|
|
" replacedString = \"\\n- title: %s\\n url: /%s/%s\\n%s expand_sections: true\\n sections: \" % (title, caseSensitiveFolderName, urlValue, ' not_numbered: true\\n' if markdownExists else '')\n",
|
|
" result = result.replace(header, replacedString)\n",
|
|
" if (markdownExists):\n",
|
|
" result = result.replace(urls[index], '')\n",
|
|
" del urls[index]\n",
|
|
" if (urls):\n",
|
|
" for url in urls:\n",
|
|
" title = url[url.rindex(path.sep)+1:].rstrip()\n",
|
|
" urlValue = title\n",
|
|
" if (len(contentFolders) > 0):\n",
|
|
" folders = url[7:].split(path.sep)\n",
|
|
" if (folders[len(folders)-2] in contentFolders):\n",
|
|
" parentFolder = contentFolders.index(folders[len(folders)-2])\n",
|
|
" urlValue = \"%s/%s\" % (contentFolders[parentFolder], title)\n",
|
|
" replacedString = \"\\n - title: %s\\n url: /%s\" % (title, urlValue)\n",
|
|
" else:\n",
|
|
" replacedString = \"\\n - title: %s\\n url: /%s\" % (title, urlValue) if rootmarkdownExists else \"\\n- title: %s\\n url: /%s\" % (title, urlValue)\n",
|
|
" result = result.replace(url, replacedString)\n",
|
|
" fwrite = open(tocFilePath, \"w\")\n",
|
|
" fwrite.write(result)\n",
|
|
" fwrite.close()\n",
|
|
" # formattinf any left over urls in the file\n",
|
|
" elif (urls):\n",
|
|
" for url in urls:\n",
|
|
" title = url[url.rindex(path.sep)+1:].rstrip()\n",
|
|
" urlValue = title\n",
|
|
" replacedString = \"\\n - title: %s\\n url: /%s\" % (title, urlValue) if rootmarkdownExists else \"\\n- title: %s\\n url: /%s\" % (title, urlValue)\n",
|
|
" result = result.replace(url, replacedString)\n",
|
|
" fwrite = open(tocFilePath, \"w\")\n",
|
|
" fwrite.write(result)\n",
|
|
" fwrite.close()\n",
|
|
" else:\n",
|
|
" raise SystemExit(f'\\n File Name contains unsupported-characters (ex: underscores) by Jupyter Book.\\n')\n",
|
|
" # Update the Book title in config file\n",
|
|
" configFilePath = path.join(book_name, \"_config.yml\")\n",
|
|
" f = open(configFilePath, \"r\")\n",
|
|
" result = f.read()\n",
|
|
" f.close()\n",
|
|
" titleLine = re.search(r'title: [a-zA-Z0-9\\\\.\\s\\-\\/]+$', result, re.MULTILINE).group()\n",
|
|
" title = 'title: %s' % (path.splitext(path.basename(book_name))[0])\n",
|
|
" result = result.replace(titleLine, title)\n",
|
|
" fwrite = open(configFilePath, \"w\")\n",
|
|
" fwrite.write(result)\n",
|
|
" fwrite.close()\n",
|
|
" # cleanup the directories\n",
|
|
" with os.scandir(book_name) as root_dir:\n",
|
|
" for path in root_dir:\n",
|
|
" if path.is_file() and path.name not in ('_config.yml'):\n",
|
|
" os.remove(path)\n",
|
|
" if path.is_dir() and path.name not in ('_data', 'content'):\n",
|
|
" shutil.rmtree(path)\n",
|
|
" except Exception as e:\n",
|
|
" raise SystemExit(str(e))\n",
|
|
"else:\n",
|
|
" tocFilePath = path.join(book_name, \"_toc.yml\")\n",
|
|
" configFilePath = path.join(book_name, \"_config.yml\")\n",
|
|
" visited = []\n",
|
|
" # modify generated toc file\n",
|
|
" with open(tocFilePath, 'r') as stream:\n",
|
|
" data = yaml.safe_load(stream)\n",
|
|
" if not isinstance(data, list):\n",
|
|
" new_data = []\n",
|
|
" for k in data:\n",
|
|
" if k == 'file':\n",
|
|
" new_data.append({k : data[k]})\n",
|
|
" elif k == 'sections':\n",
|
|
" new_data[-1].update({'numbered' : 'false'})\n",
|
|
" new_data[-1].update({'expand_sections' : 'true'})\n",
|
|
" new_data[-1].update({k : data[k]})\n",
|
|
" data = new_data\n",
|
|
" for k in data:\n",
|
|
" if 'sections' in k:\n",
|
|
" getAllSections([], data, k['sections'])\n",
|
|
"\n",
|
|
" with open(tocFilePath, 'w') as outfile:\n",
|
|
" yaml.dump(data, outfile, sort_keys=False)\n",
|
|
" # create config file\n",
|
|
" config = {}\n",
|
|
" config['title'] = path.basename(book_name).title()\n",
|
|
" with open(configFilePath, 'w') as output:\n",
|
|
" yaml.dump(config, output, default_flow_style=False)\n",
|
|
""
|
|
],
|
|
"metadata": {
|
|
"azdata_cell_guid": "6124730b-f52e-4103-8dbb-e3a62325fb55",
|
|
"tags": [
|
|
"hide_input"
|
|
]
|
|
},
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## 4. Open your Book!\r\n",
|
|
"**Run the below cell and click on the link to view your book in Azure Data Studio.**"
|
|
],
|
|
"metadata": {
|
|
"azdata_cell_guid": "ab100e5c-13f4-484a-9a4a-49bb13cad027"
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": [
|
|
"import re, os\r\n",
|
|
"from IPython.display import *\r\n",
|
|
"if os.name == 'nt':\r\n",
|
|
" bookPath = book_name.replace('\\\\', '\\\\\\\\')\r\n",
|
|
" display(HTML(\"<h2><b><a href=\\\"command:bookTreeView.openBook?"\"+str(bookPath)+\""\\\"><font size=\\\"3\\\">Click here to open your Book in ADS</font></a></b></h2>\"))\r\n",
|
|
"else:\r\n",
|
|
" display(HTML(\"<h2><b><a href=\\\"command:bookTreeView.openBook?"\"+str(book_name)+\""\\\"><font size=\\\"3\\\">Click here to open your Book in ADS</font></a></b></h2>\"))"
|
|
],
|
|
"metadata": {
|
|
"azdata_cell_guid": "33d8e1cb-1eec-41ed-a368-1aeef9af62d4",
|
|
"tags": [
|
|
"hide_input"
|
|
]
|
|
},
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"<span style=\"color:red\">**Note**: On clicking the above link, we create a temporary toc.yml file for your convenience.</span>\r\n",
|
|
"\r\n",
|
|
"**For versions < 0.7.0**\r\n",
|
|
"\r\n",
|
|
" Please update that file inside your book (located at: *YourbookPath*/_data/toc.yml) if you want to further customize your book following \r\n",
|
|
" instructions at https://legacy.jupyterbook.org/guide/01-5_tour.html#Table-of-Contents.\r\n",
|
|
"\r\n",
|
|
"**For the newer versions**\r\n",
|
|
"\r\n",
|
|
"Please update the _toc.yml file inside your book (located at: YourbookPath/_toc.yml). And refer to the documentation at https://jupyterbook.org/customize/toc.html for further customization."
|
|
],
|
|
"metadata": {
|
|
"azdata_cell_guid": "d193d588-847b-4725-9591-098d0fb24343"
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": [
|
|
"display(HTML(\"<h1><b>That's it!</b></h1><br/><p>You are good to view your book in Azure Data Studio by clicking on the above link.</p>\"))"
|
|
],
|
|
"metadata": {
|
|
"azdata_cell_guid": "bd2fe173-66ce-48b3-8dc3-c4d7560953c8",
|
|
"tags": [
|
|
"hide_input"
|
|
]
|
|
},
|
|
"outputs": [],
|
|
"execution_count": null
|
|
}
|
|
]
|
|
} |