From ee045951097e890411c19c6d764fcc7efc7c1e97 Mon Sep 17 00:00:00 2001
From: Jeremy Singer-Vine <jsvine@gmail.com>
Date: Tue, 15 Dec 2015 11:40:14 -0500
Subject: [PATCH] Remove pandas and bump to 0.0.2

---
 README.md              | 87 ++++++++++++++++++++++++++++++++++++++----
 pdfplumber/__init__.py |  2 +-
 setup.py               |  6 +--
 tox.ini                |  1 -
 4 files changed, 83 insertions(+), 13 deletions(-)

diff --git a/README.md b/README.md
index 19335eb..bd1dcff 100644
--- a/README.md
+++ b/README.md
@@ -2,19 +2,20 @@ __WARNING: This software is in its very early days, might not work well, and mig
 
 # PDFPlumber
 
-Plumb a PDF for detailed information about each char, rectangle, line, et cetera.
+Plumb a PDF for detailed information about each text character, rectangle, line, and image.
 
-Built on [`pdfminer`](https://github.com/euske/pdfminer)/[`pdfminer.six`](https://github.com/goulu/pdfminer).
+Built on [`pdfminer`](https://github.com/euske/pdfminer) and [`pdfminer.six`](https://github.com/goulu/pdfminer).
 
 ## Installation
 
 ```sh
-pip install git+https://github.com/goulu/pdfminer#egg=pdfminer.six
 pip install pdfplumber
 ```
 
 ## Usage
 
+### Basic Example
+
 ```python
 import pdfplumber
 
@@ -25,14 +26,84 @@ pdf = pdfplumber.from_path("path/to/file.pdf")
 with open("path/to/file.pdf") as f:
     pdf = pdfplumber.load(f)
 
-print(pdf.chars)
-print(pdf.rects)
-print(pdf.lines)
+if len(pdf.chars):
+    print(pdf.chars[0])
+
+if len(pdf.rects):
+    print(pdf.rects[0])
+
+if len(pdf.lines):
+    print(pdf.lines[0])
 ```
 
-### Pandas Integration
+### Loading a PDF
 
-By default, `pdf.chars`, etc., will be a plain Python dictionary. But if you `pandas=True` to `pdfplumber.load`/`.from_file`, you'll receive those properties as [Pandas dataframes](http://pandas.pydata.org/pandas-docs/stable/dsintro.html#dataframe). 
+`pdfplumber` provides two main ways to load a PDF:
+    - `pdfplumber.load(file_like_object)`
+    - `pdfplumber.from_path("path/to/file.pdf")`
+
+Both methods return an instance of the `pdfplumber.PDF` class.
+
+### Objects
+
+Each instance of `pdfplumber.PDF` provides access to six types of PDF objects. The following properties each return a Python list of the matching objects:
+    - `.chars`, each representing a single text character.
+    - `.annos`, each representing a single annotation-text character.
+    - `.lines`, each representing a single 1-dimensional line.
+    - `.rects`, each representing a single 2-dimensional rectangle.
+    - `.images`, each representing a single image.
+    - `.figures`, each representing a single figure.
+
+### Object Properties
+
+Each object is represented as a simple Python `dict`, with the following properties:
+
+- `char` / `anno`:
+    - `pageid`: Page ID on which this character was found.
+    - `text`: E.g., "z", or "Z" or " ".
+    - `fontname`: Name of the character's font face.
+    - `size`: Font size.
+    - `adv`: Equal to text width * the font size * scaling factor.
+    - `upright`: Whether the character is upright.
+    - `height`: Height of the character.
+    - `width`: Width of the character.
+    - `x0`: Distance of left side of character from left side of page.
+    - `x1`: Distance of right side of character from left side of page.
+    - `y0`: Distance of bottom of character from bottom of page.
+    - `y1`: Distance of top of character from bottom of page.
+    - `top`: Distance of top of character from top of page.
+    - `doctop`: Distance of top of character from top of document.
+    - `kind`: "LTChar" / "LTAnno"
+
+- `line`:
+    - `pageid`: Page ID on which this line was found.
+    - `height`: Height of line.
+    - `width`: Width of line.
+    - `x0`: Distance of left-side extremity from left side of page.
+    - `x1`: Distance of right-side extremity from left side of page.
+    - `y0`: Distance of bottom extremity from bottom of page.
+    - `y1`: Distance of top extremity bottom of page.
+    - `top`: Distance of top of line from top of page.
+    - `doctop`: Distance of top of line from top of document.
+    - `linewidth`: Thickness of line.
+    - `kind`: "LTLine"
+
+- `rect`:
+    - `pageid`: Page ID on which this rectangle was found.
+    - `height`: Height of rectangle.
+    - `width`: Width of rectangle.
+    - `x0`: Distance of left side of rectangle from left side of page.
+    - `x1`: Distance of right side of rectangle from left side of page.
+    - `y0`: Distance of bottom of rectangle from bottom of page.
+    - `y1`: Distance of top of rectangle from bottom of page.
+    - `top`: Distance of top of rectangle from top of page.
+    - `doctop`: Distance of top of rectangle from top of document.
+    - `linewidth`: Thickness of line.
+    - `kind`: "LTRect"
+
+- `image`: TK
+
+- `figure`: TK
 
 ## Python Support
 
diff --git a/pdfplumber/__init__.py b/pdfplumber/__init__.py
index c3946d1..e75d72a 100644
--- a/pdfplumber/__init__.py
+++ b/pdfplumber/__init__.py
@@ -3,7 +3,7 @@ import pdfminer
 import pdfminer.pdftypes
 pdfminer.pdftypes.STRICT = False
 
-VERSION_TUPLE = (0, 0, 1)
+VERSION_TUPLE = (0, 0, 2)
 VERSION = ".".join(map(str, VERSION_TUPLE))
 
 def load(file_or_buffer, **kwargs):
diff --git a/setup.py b/setup.py
index 786471d..5d7615d 100644
--- a/setup.py
+++ b/setup.py
@@ -5,13 +5,13 @@ import subprocess
 base_reqs = [
     "chardet",
     "pycrypto",
-    "pdfminer.six"
+    "pdfminer.six>=20151013"
 ]
 
 setup(
     name="pdfplumber",
-    version="0.0.1",
+    version="0.0.2",
     packages=find_packages(exclude=["test",]),
-    tests_require=[ "nose", "pandas" ] + base_reqs,
+    tests_require=[ "nose", "pandas>=0.17.1" ] + base_reqs,
     install_requires=base_reqs,
 )
diff --git a/tox.ini b/tox.ini
index 6ad9cfa..6942ab1 100644
--- a/tox.ini
+++ b/tox.ini
@@ -4,5 +4,4 @@ envlist = py27,py31,py34
 [testenv]
 deps=nose
      pandas
-     git+https://github.com/goulu/pdfminer#egg=pdfminer.six
 commands=nosetests