code and docs update

static/docs/tools/parallel/kings_ii_TF.ipynb → static/docs/tools/parallel/kings_ii_legacy.ipynb

@@ -71,7 +71,18 @@
     "collapsed": false,
     "scrolled": true
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0.00s This is LAF-Fabric 4.5.19\n",
+      "API reference: http://laf-fabric.readthedocs.org/en/latest/texts/API-reference.html\n",
+      "Feature doc: https://shebanq.ancient-data.org/static/docs/featuredoc/texts/welcome.html\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "import sys,os, re, pickle\n",
     "import collections, difflib\n",
@@ -83,7 +94,11 @@
     "import matplotlib.pyplot as plt\n",
     "%matplotlib inline\n",
     "\n",
-    "from tf.fabric import Fabric"
+    "import laf\n",
+    "from laf.fabric import LafFabric\n",
+    "from etcbc.preprocess import prepare\n",
+    "from etcbc.lib import Transcription\n",
+    "fabric = LafFabric()"
    ]
   },
   {
@@ -92,16 +107,11 @@
    "source": [
     "## 0.3 Data source\n",
     "\n",
-    "We use the ETCBC database in its version 4c, downloadable from the GitHub repo\n",
-    "[text-fabric-data](https://github.com/ETCBC/text-fabric-data).\n",
-    "The format of the data obtained through Github is immediately ready to be used by Text-Fabric,\n",
-    "and hence by this notebook as well.\n",
-    "\n",
-    "A previous version of this notebook was based on version 4b,\n",
-    "as archived at DANS, downloadable via DOI\n",
+    "We use the ETCBC database in its version 4b, as archived at DANS, downloadable via DOI\n",
     "[10.17026/dans-z6y-skyh](http://dx.doi.org/10.17026/dans-z6y-skyh).\n",
     "It is also possible to get this data through Github:\n",
     "[etcbc/laf-fabric-data](https://github.com/ETCBC/laf-fabric-data).\n",
+    "The format of the data obtained through Github is immediately ready to be used by LAF-Fabric, and hence by this notebook as well.\n",
     "\n",
     "The transcription of 1QIsa<sup>a</sup> is in a file produced by the ETCBC. This file is included \n",
     "[here](https://shebanq.ancient-data.org/shebanq/static/docs/tools/parallel/1QIsaa_an.txt)\n",
@@ -118,7 +128,7 @@
    "outputs": [],
    "source": [
     "source = 'etcbc'\n",
-    "version = '4c'\n",
+    "version = '4b'\n",
     "QISA_FILE = '1QIsaa_an.txt'"
    ]
   },
@@ -139,54 +149,43 @@
    "cell_type": "code",
    "execution_count": 3,
    "metadata": {
-    "collapsed": false
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "This is Text-Fabric 1.2.7\n",
-      "Api reference : https://github.com/ETCBC/text-fabric/wiki/Api\n",
-      "Tutorial      : https://github.com/ETCBC/text-fabric/blob/master/docs/tutorial.ipynb\n",
-      "Data sources  : https://github.com/ETCBC/text-fabric-data\n",
-      "Data docs     : https://etcbc.github.io/text-fabric-data/features/hebrew/etcbc4c/0_overview.html\n",
-      "Shebanq docs  : https://shebanq.ancient-data.org/text\n",
-      "Slack team    : https://shebanq.slack.com/signup\n",
-      "Questions? Ask shebanq@ancient-data.org for an invite to Slack\n",
-      "107 features found and 0 ignored\n"
-     ]
-    }
-   ],
-   "source": [
-    "ETCBC = 'hebrew/{}{}'.format(source, version)\n",
-    "TF = Fabric( modules=ETCBC )"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "scrolled": true
    },
    "outputs": [
     {
-     "name": "stdout",
+     "name": "stderr",
      "output_type": "stream",
      "text": [
-      "  0.00s loading features ...\n",
-      "   |     0.00s M otext                from /Users/dirk/github/text-fabric-data/hebrew/etcbc4c\n",
-      "   |     0.19s B lex_utf8             from /Users/dirk/github/text-fabric-data/hebrew/etcbc4c\n",
-      "   |     0.13s B language             from /Users/dirk/github/text-fabric-data/hebrew/etcbc4c\n",
-      "  4.37s All features loaded/computed - for details use loadLog()\n"
+      "  0.00s LOADING API: please wait ... \n",
+      "  0.00s USING main  DATA COMPILED AT: 2015-11-02T15-08-56\n",
+      "  0.00s USING annox DATA COMPILED AT: 2016-01-27T19-01-17\n",
+      "  3.04s LOGFILE=/Users/dirk/laf-fabric-output/etcbc4b/kings/__log__kings.txt\n",
+      "  3.04s INFO: LOADING PREPARED data: please wait ... \n",
+      "  3.04s prep prep: G.node_sort\n",
+      "  3.18s prep prep: G.node_sort_inv\n",
+      "  3.73s prep prep: L.node_up\n",
+      "  7.52s prep prep: L.node_down\n",
+      "    13s prep prep: V.verses\n",
+      "    13s prep prep: V.books_la\n",
+      "    13s ETCBC reference: http://laf-fabric.readthedocs.org/en/latest/texts/ETCBC-reference.html\n",
+      "    15s INFO: LOADED PREPARED data\n",
+      "    15s INFO: DATA LOADED FROM SOURCE etcbc4b AND ANNOX lexicon FOR TASK kings AT 2016-03-04T15-50-30\n"
      ]
     }
    ],
    "source": [
-    "api = TF.load('''\n",
-    "    language lex_utf8\n",
-    "''')\n",
-    "api.makeAvailableIn(globals())"
+    "API = fabric.load(source+version, 'lexicon', 'kings', {\n",
+    "    \"xmlids\": {\"node\": False, \"edge\": False},\n",
+    "    \"features\": ('''\n",
+    "        otype\n",
+    "        language lex_utf8\n",
+    "        book chapter verse\n",
+    "    ''',''),\n",
+    "    \"prepare\": prepare,\n",
+    "    \"primary\": False,\n",
+    "}, verbose='NORMAL')\n",
+    "exec(fabric.localnames.format(var='fabric'))"
    ]
   },
   {
@@ -211,71 +210,46 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 4,
    "metadata": {
     "collapsed": false
    },
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "{'am': {'language': 'ኣማርኛ', 'languageEnglish': 'amharic'},\n",
-       " 'ar': {'language': 'العَرَبِية', 'languageEnglish': 'arabic'},\n",
-       " 'bn': {'language': 'বাংলা', 'languageEnglish': 'bengali'},\n",
-       " 'da': {'language': 'Dansk', 'languageEnglish': 'danish'},\n",
-       " 'de': {'language': 'Deutsch', 'languageEnglish': 'german'},\n",
-       " 'el': {'language': 'Ελληνικά', 'languageEnglish': 'greek'},\n",
-       " 'en': {'language': 'English', 'languageEnglish': 'english'},\n",
-       " 'es': {'language': 'Español', 'languageEnglish': 'spanish'},\n",
-       " 'fa': {'language': 'فارسی', 'languageEnglish': 'farsi'},\n",
-       " 'fr': {'language': 'Français', 'languageEnglish': 'french'},\n",
-       " 'he': {'language': 'עברית', 'languageEnglish': 'hebrew'},\n",
-       " 'hi': {'language': 'हिन्दी', 'languageEnglish': 'hindi'},\n",
-       " 'id': {'language': 'Bahasa Indonesia', 'languageEnglish': 'indonesian'},\n",
-       " 'ja': {'language': '日本語', 'languageEnglish': 'japanese'},\n",
-       " 'ko': {'language': '한국어', 'languageEnglish': 'korean'},\n",
-       " 'la': {'language': 'Latina', 'languageEnglish': 'latin'},\n",
-       " 'nl': {'language': 'Nederlands', 'languageEnglish': 'dutch'},\n",
-       " 'pa': {'language': 'ਪੰਜਾਬੀ', 'languageEnglish': 'punjabi'},\n",
-       " 'pt': {'language': 'Português', 'languageEnglish': 'portuguese'},\n",
-       " 'ru': {'language': 'Русский', 'languageEnglish': 'russian'},\n",
-       " 'sw': {'language': 'Kiswahili', 'languageEnglish': 'swahili'},\n",
-       " 'syc': {'language': 'ܠܫܢܐ ܣܘܪܝܝܐ', 'languageEnglish': 'syriac'},\n",
-       " 'tr': {'language': 'Türkçe', 'languageEnglish': 'turkish'},\n",
-       " 'ur': {'language': 'اُردُو', 'languageEnglish': 'urdu'},\n",
-       " 'yo': {'language': 'èdè Yorùbá', 'languageEnglish': 'yoruba'},\n",
-       " 'zh': {'language': '中文', 'languageEnglish': 'chinese'}}"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ar: arabic     (aka العَرَبِية)\n",
+      "de: german     (aka Deutsch)\n",
+      "el: greek      (aka Ελληνικά)\n",
+      "en: english    (aka English)\n",
+      "es: spanish    (aka Español)\n",
+      "fr: french     (aka François)\n",
+      "he: hebrew     (aka עברית)\n",
+      "id: indonesian (aka Bahasa Indonesia)\n",
+      "ko: korean     (aka 한국어)\n",
+      "la: latin      (aka Latina)\n",
+      "nl: dutch      (aka Nederlands)\n",
+      "ru: russian    (aka Русский)\n",
+      "sw: swahili    (aka Kiswahili)\n",
+      "tr: turkish    (aka Türkçe)\n",
+      "zh: chinese    (aka 中文)\n"
+     ]
     }
    ],
    "source": [
-    "T.languages"
+    "for (ln, (en_name, own_name)) in sorted(T.langs.items()): \n",
+    "    print('{}: {:<10} (aka {})'.format(ln, en_name, own_name))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 5,
    "metadata": {
     "collapsed": false,
     "scrolled": true
    },
-   "outputs": [
-    {
-     "ename": "NameError",
-     "evalue": "name 'API' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-8-63cd9d63b4d9>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      9\u001b[0m \u001b[0mCROSSREF_APP\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'parallel'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     10\u001b[0m \u001b[0;31m# directory of computed intermediary results of parallel.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 11\u001b[0;31m \u001b[0mPRECOMP_DIR\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'{}/{}{}/{}/{}'\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mAPI\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'output_dir'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msource\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mversion\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mCROSSREF_APP\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'stored'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     12\u001b[0m \u001b[0;31m# precomputed list of verse chunks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     13\u001b[0m \u001b[0mCHUNK_GREP\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'{}/chunks/chunk_{}_{}'\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mPRECOMP_DIR\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'O'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'verse'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mNameError\u001b[0m: name 'API' is not defined"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# the language of the book names\n",
     "LANG = 'en'\n",