{"cells": [{"cell_type": "markdown", "metadata": {}, "source": ["# Example with re2\n", "\n", "*wrapclib* wraps the library [re2](https://github.com/google/re2) using the wrapper [pyre2](https://github.com/facebook/pyre2)."]}, {"cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [{"data": {"text/html": ["<div id=\"my_id_menu_nb\">run previous cell, wait for 2 seconds</div>\n", "<script>\n", "function repeat_indent_string(n){\n", "    var a = \"\" ;\n", "    for ( ; n > 0 ; --n)\n", "        a += \"    \";\n", "    return a;\n", "}\n", "// look up into all sections and builds an automated menu //\n", "var update_menu_string = function(begin, lfirst, llast, sformat, send, keep_item, begin_format, end_format) {\n", "    var anchors = document.getElementsByClassName(\"section\");\n", "    if (anchors.length == 0) {\n", "        anchors = document.getElementsByClassName(\"text_cell_render rendered_html\");\n", "    }\n", "    var i,t;\n", "    var text_menu = begin;\n", "    var text_memo = \"<pre>\\nlength:\" + anchors.length + \"\\n\";\n", "    var ind = \"\";\n", "    var memo_level = 1;\n", "    var href;\n", "    var tags = [];\n", "    var main_item = 0;\n", "    var format_open = 0;\n", "    for (i = 0; i <= llast; i++)\n", "        tags.push(\"h\" + i);\n", "\n", "    for (i = 0; i < anchors.length; i++) {\n", "        text_memo += \"**\" + anchors[i].id + \"--\\n\";\n", "\n", "        var child = null;\n", "        for(t = 0; t < tags.length; t++) {\n", "            var r = anchors[i].getElementsByTagName(tags[t]);\n", "            if (r.length > 0) {\n", "child = r[0];\n", "break;\n", "            }\n", "        }\n", "        if (child == null) {\n", "            text_memo += \"null\\n\";\n", "            continue;\n", "        }\n", "        if (anchors[i].hasAttribute(\"id\")) {\n", "            // when converted in RST\n", "            href = anchors[i].id;\n", "            text_memo += \"#1-\" + href;\n", "            // passer \u00e0 child suivant (le chercher)\n", "        }\n", "        else if (child.hasAttribute(\"id\")) {\n", "            // in a notebook\n", "            href = child.id;\n", "            text_memo += \"#2-\" + href;\n", "        }\n", "        else {\n", "            text_memo += \"#3-\" + \"*\" + \"\\n\";\n", "            continue;\n", "        }\n", "        var title = child.textContent;\n", "        var level = parseInt(child.tagName.substring(1,2));\n", "\n", "        text_memo += \"--\" + level + \"?\" + lfirst + \"--\" + title + \"\\n\";\n", "\n", "        if ((level < lfirst) || (level > llast)) {\n", "            continue ;\n", "        }\n", "        if (title.endsWith('\u00b6')) {\n", "            title = title.substring(0,title.length-1).replace(\"<\", \"&lt;\")\n", "         .replace(\">\", \"&gt;\").replace(\"&\", \"&amp;\");\n", "        }\n", "        if (title.length == 0) {\n", "            continue;\n", "        }\n", "\n", "        while (level < memo_level) {\n", "            text_menu += end_format + \"</ul>\\n\";\n", "            format_open -= 1;\n", "            memo_level -= 1;\n", "        }\n", "        if (level == lfirst) {\n", "            main_item += 1;\n", "        }\n", "        if (keep_item != -1 && main_item != keep_item + 1) {\n", "            // alert(main_item + \" - \" + level + \" - \" + keep_item);\n", "            continue;\n", "        }\n", "        while (level > memo_level) {\n", "            text_menu += \"<ul>\\n\";\n", "            memo_level += 1;\n", "        }\n", "        text_menu += repeat_indent_string(level-2);\n", "        text_menu += begin_format + sformat.replace(\"__HREF__\", href).replace(\"__TITLE__\", title);\n", "        format_open += 1;\n", "    }\n", "    while (1 < memo_level) {\n", "        text_menu += end_format + \"</ul>\\n\";\n", "        memo_level -= 1;\n", "        format_open -= 1;\n", "    }\n", "    text_menu += send;\n", "    //text_menu += \"\\n\" + text_memo;\n", "\n", "    while (format_open > 0) {\n", "        text_menu += end_format;\n", "        format_open -= 1;\n", "    }\n", "    return text_menu;\n", "};\n", "var update_menu = function() {\n", "    var sbegin = \"\";\n", "    var sformat = '<a href=\"#__HREF__\">__TITLE__</a>';\n", "    var send = \"\";\n", "    var begin_format = '<li>';\n", "    var end_format = '</li>';\n", "    var keep_item = -1;\n", "    var text_menu = update_menu_string(sbegin, 2, 4, sformat, send, keep_item,\n", "       begin_format, end_format);\n", "    var menu = document.getElementById(\"my_id_menu_nb\");\n", "    menu.innerHTML=text_menu;\n", "};\n", "window.setTimeout(update_menu,2000);\n", "            </script>"], "text/plain": ["<IPython.core.display.HTML object>"]}, "execution_count": 2, "metadata": {}, "output_type": "execute_result"}], "source": ["from jyquickhelper import add_notebook_menu\n", "add_notebook_menu()"]}, {"cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": ["from wrapclib import re2"]}, {"cell_type": "markdown", "metadata": {}, "source": ["## Example with HTML"]}, {"cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["('<h1>mot</h1>',)\n"]}], "source": ["import re\n", "s = \"<h1>mot</h1>\"\n", "print(re.compile(\"(<.*>)\").match(s).groups())"]}, {"cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["('<h1>mot</h1>',)\n"]}], "source": ["s = \"<h1>mot</h1>\"\n", "print(re2.compile(\"(<.*>)\").match(s).groups())"]}, {"cell_type": "markdown", "metadata": {}, "source": ["## Group, Span"]}, {"cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [{"data": {"text/plain": ["('14/9/2000', '20')"]}, "execution_count": 6, "metadata": {}, "output_type": "execute_result"}], "source": ["s = \"\"\"date 0 : 14/9/2000\n", "date 1 : 20/04/1971     date 2 : 14/09/1913     date 3 : 2/3/1978\n", "date 4 : 1/7/1986     date 5 : 7/3/47     date 6 : 15/10/1914\n", "date 7 : 08/03/1941     date 8 : 8/1/1980     date 9 : 30/6/1976\"\"\"\n", "\n", "expression = re2.compile(\n", "    \"([0-3]?[0-9]/[0-1]?[0-9]/([0-2][0-9])?[0-9][0-9])[^\\d]\")\n", "expression.search(s).group(1, 2)"]}, {"cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [{"data": {"text/plain": ["'14/9/2000'"]}, "execution_count": 7, "metadata": {}, "output_type": "execute_result"}], "source": ["c = expression.search(s).span(1)\n", "s[c[0]:c[1]]"]}, {"cell_type": "markdown", "metadata": {}, "source": ["## Names"]}, {"cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["{'aa': '2010', 'jj': '05', 'mm': '22'}\n"]}], "source": ["date = \"05/22/2010\"\n", "exp = \"(?P<jj>[0-9]{1,2})/(?P<mm>[0-9]{1,2})/(?P<aa>((19)|(20))[0-9]{2})\"\n", "com = re2.compile(exp)\n", "print(com.search(date).groupdict())"]}, {"cell_type": "markdown", "metadata": {}, "source": ["## findall\n", "\n", "*findall* is not natively implemented in *re2*. It was added."]}, {"cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [{"data": {"text/plain": ["[('14/9/2000', '20'),\n", " ('20/04/1971', '19'),\n", " ('14/09/1913', '19'),\n", " ('2/3/1978', '19'),\n", " ('1/7/1986', '19'),\n", " ('7/3/47', None),\n", " ('15/10/1914', '19'),\n", " ('08/03/1941', '19'),\n", " ('8/1/1980', '19')]"]}, "execution_count": 9, "metadata": {}, "output_type": "execute_result"}], "source": ["s = \"\"\"date 0 : 14/9/2000\n", "date 1 : 20/04/1971     date 2 : 14/09/1913     date 3 : 2/3/1978\n", "date 4 : 1/7/1986     date 5 : 7/3/47     date 6 : 15/10/1914\n", "date 7 : 08/03/1941     date 8 : 8/1/1980     date 9 : 30/6/1976\"\"\"\n", "\n", "expression = re2.compile(\n", "    \"([0-3]?[0-9]/[0-1]?[0-9]/([0-2][0-9])?[0-9][0-9])[^\\d]\")\n", "\n", "re2.findall(expression, s)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["## benchmark"]}, {"cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["10.5 \u00b5s \u00b1 296 ns per loop (mean \u00b1 std. dev. of 7 runs, 100000 loops each)\n"]}], "source": ["s = \"\"\"date 0 : 14/9/2000\n", "date 1 : 20/04/1971     date 2 : 14/09/1913     date 3 : 2/3/1978\n", "date 4 : 1/7/1986     date 5 : 7/3/47     date 6 : 15/10/1914\n", "date 7 : 08/03/1941     date 8 : 8/1/1980     date 9 : 30/6/1976\"\"\"\n", "\n", "expression = re.compile(\n", "    \"([0-3]?[0-9]/[0-1]?[0-9]/([0-2][0-9])?[0-9][0-9])[^\\d]\")\n", "\n", "%timeit expression.findall(s)"]}, {"cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["18.4 \u00b5s \u00b1 1.51 \u00b5s per loop (mean \u00b1 std. dev. of 7 runs, 10000 loops each)\n"]}], "source": ["%timeit re2.findall(expression, s)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["That's expected as method *findall* is implemented in python and not C."]}, {"cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": []}], "metadata": {"kernelspec": {"display_name": "Python 3", "language": "python", "name": "python3"}, "language_info": {"codemirror_mode": {"name": "ipython", "version": 3}, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.2"}}, "nbformat": 4, "nbformat_minor": 2}