etree bug function namespace prefix

etree_test.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from lxml import etree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "etree.FunctionNamespace(\"http://exslt.org/regular-expressions\").prefix = 're'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "text = \"\"\"\n",
    "<monthEntity month=\"02\" year=\"1998\">\n",
    "    <article>\n",
    "        <full_text> Some article text </full_text>\n",
    "        <full_text> Some more article text fragment 2 </full_text>\n",
    "    </article>\n",
    "</monthEntity>\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "t = etree.fromstring(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "search = etree.XPath('//full_text[re:match(text(), \"fragment\")]')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<Element full_text at 0x7f92d416cc88>]"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "search(t)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "XPathFunctionError",
     "evalue": "XPath function '{�O�\u0001}match' not found",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mXPathFunctionError\u001b[0m                        Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-58-d7ae80ab29da>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0msearch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mt\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32msrc/lxml/xpath.pxi\u001b[0m in \u001b[0;36mlxml.etree.XPath.__call__ (src/lxml/lxml.etree.c:172853)\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32msrc/lxml/xpath.pxi\u001b[0m in \u001b[0;36mlxml.etree._XPathEvaluatorBase._handle_result (src/lxml/lxml.etree.c:170157)\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32msrc/lxml/lxml.etree.pyx\u001b[0m in \u001b[0;36mlxml.etree._ExceptionContext._raise_if_stored (src/lxml/lxml.etree.c:12061)\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;31mXPathFunctionError\u001b[0m: XPath function '{�O�\u0001}match' not found"
     ]
    }
   ],
   "source": [
    "search(t)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'3.7.2'"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "etree.__version__"
   ]
  }
 ],
 "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}

test.py

from lxml import etree

etree.FunctionNamespace("http://exslt.org/regular-expressions").prefix = 're'

text = """
<monthEntity month="02" year="1998">
    <article>
        <full_text> Some article text </full_text>
        <full_text> Some more article text fragment 2 </full_text>
    </article>
</monthEntity>
"""
t = etree.fromstring(text)
search = etree.XPath('//full_text[re:match(text(), "fragment")]')
search(t) # this one works. returns a list with 1 element
search(t) # this one fails with 
# src/lxml/xpath.pxi in lxml.etree.XPath.__call__ (src/lxml/lxml.etree.c:172853)()
# ...
# XPathFunctionError: XPath function '{�{|
}match' not found

# The thing before `match` in curly braces sometimes changes on different runs of the program
# So this could be a bug somewhere
# using etree.__version__ 3.7.2