Python code to generate a list of labels from latex documents.

LatexLabelList.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# List All Labels\n",
    "\n",
    "This notebook will list all the labels in my thesis. My labels are all like `chp:Chapter_Name`, `fig:figure_name`, `eq:equation`, etc. The patterns `patt`, and/or `app_patt` can be modified to suit different label naming conventions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "chdir = '/home/jkibele/Documents/code_projects/PhDThesis/'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# reg exp to find full label specifications\n",
    "patt = re.compile(\"\\\\label{(\\w*:\\w*)}\")\n",
    "# reg exp to find `addtotoc` labels\n",
    "app_patt = re.compile(\"(\\w+:\\w+)\")\n",
    "\n",
    "lbls = []\n",
    "for root, dirs, files in os.walk(chdir):\n",
    "    for fn in files: \n",
    "        if fn == 'main.tex':\n",
    "            # my project has some appendices that are pulled into\n",
    "            # the project using includepdf and the labels for these\n",
    "            # are specified using `addtotoc`. This if statement\n",
    "            # finds those labels in main.tex.\n",
    "            with open(os.path.join(root, fn)) as f:\n",
    "                lbls.extend(re.findall(app_patt, f.read()))\n",
    "        elif fn.endswith(\".tex\") and fn<>\"zTemplateChapter1.tex\":\n",
    "            # there's a template file in my project that I don't\n",
    "            # want to search for labels.\n",
    "            with open(os.path.join(root,fn)) as f:\n",
    "                txt = f.read()\n",
    "                labels = re.findall(patt, txt)\n",
    "                lbls.extend(labels)\n",
    "typs = []\n",
    "names = []\n",
    "for lbl in lbls:\n",
    "    t, n = lbl.split(':')\n",
    "    typs.append(t)\n",
    "    names.append(n)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "df = pd.DataFrame({'typ':typs, 'nam':names})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "app:\n",
      "    depth_param_est\n",
      "    param_est\n",
      "    preprocessing\n",
      "    water_column\n",
      "\n",
      "chp:\n",
      "    BPS\n",
      "    Depth\n",
      "    Intro\n",
      "    OpticalRS\n",
      "    ParamEst\n",
      "    Water\n",
      "\n",
      "sec:\n",
      "    curve_fit_est\n",
      "    lin_reg_est\n",
      "\n",
      "fig:\n",
      "    bps_fig1\n",
      "    pd_K_ests\n",
      "    pe_curve_fit\n",
      "    pe_dwm_bars\n",
      "    pe_linear_K_est\n",
      "    pe_linear_K_est_dr\n",
      "    pe_location_map\n",
      "    pe_surf_corr_K\n",
      "    wcc_depths\n",
      "    wcc_imgcomp\n",
      "    wcc_location_map\n",
      "    wcc_method_comp\n",
      "    wcc_parallel\n",
      "\n",
      "tab:\n",
      "    est_parameters\n",
      "\n",
      "eq:\n",
      "    albedo_plus\n",
      "    geometric_factor\n",
      "    k_from_slope\n",
      "    linregress\n",
      "    lyz_model_sag\n",
      "    lyz_model_transformed\n",
      "    lyz_shallow_water\n",
      "    lyz_transform\n",
      "    mar_sag_comp\n",
      "    mar_wcc\n",
      "    maritorena9a\n",
      "    maritorena_albedo_subsurf\n",
      "    maritorena_model\n",
      "    maritorena_toa\n",
      "    refraction\n",
      "    sag_index_radiance\n",
      "    sag_ref_index\n",
      "    surf_correction\n",
      "    surf_ref\n",
      "    toa_refletance\n",
      "    toar_deep\n"
     ]
    }
   ],
   "source": [
    "for typ in set(typs):\n",
    "    print \"\\n{}:\".format(typ)\n",
    "    for lab in df[df.typ==typ]['nam'].sort_values():\n",
    "        print \"    {}\".format(lab)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

Thanks for sharing this code!

I changed some parts in the larger part of your code to make it work with Python 3.6

# import regex instead of re
import regex

# reg exp to find full label specifications
patt = regex.compile("\\label{(\w*:\w*)}")
# reg exp to find `addtotoc` labels
app_patt = re.compile("(\w+:\w+)")

lbls = []
for root, dirs, files in os.walk(chdir):
    for fn in files: 
        if fn == 'main.tex':
            # my project has some appendices that are pulled into
            # the project using includepdf and the labels for these
            # are specified using `addtotoc`. This if statement
            # finds those labels in main.tex.
            with open(os.path.join(root, fn),encoding="Latin-1") as f:
                lbls.extend(re.findall(app_patt, f.read()))
        elif fn.endswith(".tex"):
            # there's a template file in my project that I don't
            # want to search for labels.
            with open(os.path.join(root,fn),encoding="Latin-1") as f:
                txt = f.read()
                labels = regex.findall(patt, txt)
                lbls.extend(labels)
typs = []
names = []
for lbl in lbls:
    t, n = lbl.split(':')
    typs.append(t)
    names.append(n)