V1.0.1 (#2)

* Stable Version - 1.0.1

* Version Update

Author: ExtractTable

.gitignore

@@ -0,0 +1,4 @@
+/.idea/
+/dist/
+/build/
+/*.egg-info/

ExampleCode.ipynb

@@ -0,0 +1,315 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+  "colab": {
+   "name": "ExtractTable - Advanced Code Usage.ipynb",
+   "provenance": [],
+   "collapsed_sections": []
+  },
+  "kernelspec": {
+   "name": "python3",
+   "display_name": "Python 3"
+  },
+  "pycharm": {
+   "stem_cell": {
+    "cell_type": "raw",
+    "source": [],
+    "metadata": {
+     "collapsed": false
+    }
+   }
+  }
+ },
+ "cells": [
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "NhVhMrQ0ZdQr",
+    "colab_type": "code",
+    "colab": {}
+   },
+   "source": [
+    "# !pip install -U ExtractTable"
+   ],
+   "execution_count": 0,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "2aIaghfeZnQr",
+    "colab_type": "code",
+    "colab": {}
+   },
+   "source": [
+    "from ExtractTable import *"
+   ],
+   "execution_count": 0,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "LJL_ZyYzZsFY",
+    "colab_type": "code",
+    "colab": {}
+   },
+   "source": [
+    "api_key = YOUR_APIKEY_HERE"
+   ],
+   "execution_count": 0,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "bwtpzTJxZHRi",
+    "colab_type": "text"
+   },
+   "source": [
+    "**Create Session** with your API Key"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "Bfw5GTNvZGv8",
+    "colab_type": "code",
+    "colab": {}
+   },
+   "source": [
+    "et_sess = ExtractTable(api_key)"
+   ],
+   "execution_count": 0,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "On4_X8v3Zk3v",
+    "colab_type": "text"
+   },
+   "source": [
+    "**Validate** the Key and check the plan usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "a7EPvvvMZ0Ub",
+    "colab_type": "code",
+    "colab": {}
+   },
+   "source": [
+    "usage = et_sess.check_usage()"
+   ],
+   "execution_count": 0,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "sovuclERjRqy",
+    "colab_type": "text"
+   },
+   "source": [
+    "*If there is no error encountered in the above cell, it means we have a valid API key. Now, get started by checking the usage and trigger the file for processing*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "HT97IP8MZ9WF",
+    "colab_type": "code",
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 34
+    },
+    "outputId": "65f9eb37-cdec-425f-905f-c38c7d778892"
+   },
+   "source": [
+    "print(usage)"
+   ],
+   "execution_count": 6,
+   "outputs": [
+    {
+     "output_type": "stream",
+     "text": [
+      "{'credits': 1000, 'queued': 2, 'used': 533}\n"
+     ],
+     "name": "stdout"
+    }
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "-XqbBoB-i3pi",
+    "colab_type": "text"
+   },
+   "source": [
+    "**credits**: Total number credits attached to the API Key\n",
+    "\n",
+    "**queued** : Number of triggered jobs that were left \"IN_PROGRESS\", not yet retrieved\n",
+    "\n",
+    "**used**   : Number of credits already used "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "oUnBFxYiZ1Ka",
+    "colab_type": "text"
+   },
+   "source": [
+    "**Trigger** the process to extract tabular data from the file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "P_xzVgHmZ9sw",
+    "colab_type": "code",
+    "colab": {}
+   },
+   "source": [
+    "filepath = r'testimages/chervolet.jpg'\n",
+    "table_data = et_sess.process_file(filepath)"
+   ],
+   "execution_count": 0,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "XrXBfENfZ2AI",
+    "colab_type": "code",
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 255
+    },
+    "outputId": "5b97dec4-a399-44d9-c087-f86430b295e5"
+   },
+   "source": [
+    "table_data     # Notice the default output is a pandas dataframe"
+   ],
+   "execution_count": 13,
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "[            0         1      2        3              4\n",
+       " 0      vendor     Model  Price  Mileage       VIN Code\n",
+       " 1   Chevrolet  Corvette  17226  25965.0    ILLAKAWAZDZ\n",
+       " 2   Chevrolet  Corvette  34229  46429.0    RCPNSRYGXON\n",
+       " 3   Chevrolet  Corvette  27982  50209.0    NWLGCEVEHGI\n",
+       " 4   Chevrolet  Corvette  51825  72998.0    NGVZSCIZGSM\n",
+       " 5   Chevrolet  Corvette  52845  34364.0    PSDRUYYOIJG\n",
+       " 6   Chevrolet    Malibu  37874  37273.0    VLFPQPWNEFD\n",
+       " 7   Chevrolet    Malibu  15600  71441.0     EXLJGDWOZS\n",
+       " 8   Chevrolet    Malibu  52447  46700.0    NLMGJZAKBRD\n",
+       " 9   Chevrolet    Malibu  27129  36254.0  OIPFUIENLEHS)\n",
+       " 10  Chevrolet    Malibu  28846  77162.0    WRCOOFREZLL\n",
+       " 11  Chevrolet    Malibu  46165  60590.0   HUFTTHQHSFJF\n",
+       " 12  Chevrolet    Malibu  18263   377900      MHNAFSHVD]"
+      ]
+     },
+     "metadata": {
+      "tags": []
+     },
+     "execution_count": 13
+    }
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "TYLfNBQ6bL64",
+    "colab_type": "text"
+   },
+   "source": [
+    "**Whatelse** is in the store.\n",
+    "- check the latest Actual ServerResponse attached to the session with `et_sess.ServerResponse.json()`\n",
+    "- check out list of available output formats `ExtractTable._OUTPUT`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "znSqvSJbd2hv",
+    "colab_type": "text"
+   },
+   "source": [
+    "Check the **latest ServerResponse** in the processs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "cChDS1g3ds0U",
+    "colab_type": "code",
+    "colab": {}
+   },
+   "source": [
+    "et_sess.ServerResponse.json()"
+   ],
+   "execution_count": 0,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Fwu-Cn7vbEMo",
+    "colab_type": "text"
+   },
+   "source": [
+    "Check out the list of all **available output formats**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "lMlTzUsIbpx4",
+    "colab_type": "code",
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 34
+    },
+    "outputId": "68ed73b1-69a4-4f16-e909-d69409e508bd"
+   },
+   "source": [
+    "ExtractTable._OUTPUT_FORMATS"
+   ],
+   "execution_count": 16,
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "{'csv', 'dataframe', 'df', 'dict', 'json'}"
+      ]
+     },
+     "metadata": {
+      "tags": []
+     },
+     "execution_count": 16
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "glsrlvpydZaz",
+    "colab_type": "code",
+    "colab": {}
+   },
+   "source": [
+    ""
+   ],
+   "execution_count": 0,
+   "outputs": []
+  }
+ ]
+}

ExtractTable/FileOperations/__init__.py

@@ -0,0 +1,28 @@
+"""
+To validate the files at Client End; Fail Faster
+"""
+import typing as ty
+import os
+from ..exceptions import ClientFileError
+
+
+class CheckFile:
+    __SUPPORTED_EXTENSIONS__: tuple = tuple({'.pdf', '.jpeg', '.jpg', '.png'})
+    __THRESHOLD_SIZE__: int = 4      # Megabytes
+
+    def __init__(self, filepath: ty.Union[os.PathLike, str]):
+        self.filepath = filepath
+        self.type_error()
+        self.size_error()
+
+    def type_error(self) -> ty.Union[Exception, None]:
+        """To check file extension"""
+        if self.filepath.lower().endswith(self.__SUPPORTED_EXTENSIONS__):
+            return
+        raise ClientFileError(Message=f"Allowed file types are {self.__SUPPORTED_EXTENSIONS__}")
+
+    def size_error(self) -> ty.Union[Exception, None]:
+        # 1027 to create some buffer
+        if os.stat(self.filepath).st_size <= self.__THRESHOLD_SIZE__*1027*1027:
+            return
+        raise ClientFileError(Message=f"File Size greater than the threshold {self.__THRESHOLD_SIZE__} Mb.")

ExtractTable/__init__.py

@@ -0,0 +1 @@
+from .client import ExtractTable

ExtractTable/__version__.py

@@ -0,0 +1,21 @@
+VERSION = (1, 0, 1)
+PRERELEASE = None  # "alpha", "beta" or "rc"
+REVISION = None
+
+
+def generate_version(version, prerelease=None, revision=None):
+    version_parts = [".".join(map(str, version))]
+    if prerelease is not None:
+        version_parts.append("-{}".format(prerelease))
+    if revision is not None:
+        version_parts.append(".{}".format(revision))
+    return "".join(version_parts)
+
+
+__title__ = "ExtractTable"
+__description__ = "Extract tabular data from images and scanned PDFs"
+__url__ = "https://github.com/ExtractTable/ExtractTable-py"
+__version__ = generate_version(VERSION, prerelease=PRERELEASE, revision=REVISION)
+__author__ = "Saradhi"
+__author_email__ = "saradhi@extracttable.com"
+__license__ = "Apache License 2.0"