From 86348eba2f32c7e41fd1bafb4782193a3682f7fc Mon Sep 17 00:00:00 2001
From: Yusuke Shinyama <yusuke@shinyama.jp>
Date: Wed, 23 Oct 2013 00:17:12 +0900
Subject: [PATCH] Documentation updated.

---
 Makefile        |  2 +-
 README.md       | 62 +++++++++++++++++++++++++++++++++++++++++++++++++
 README.txt      |  1 -
 docs/index.html |  4 ++--
 4 files changed, 65 insertions(+), 4 deletions(-)
 create mode 100644 README.md
 delete mode 100644 README.txt

diff --git a/Makefile b/Makefile
index c6953eb..a33e2fb 100644
--- a/Makefile
+++ b/Makefile
@@ -27,7 +27,7 @@ sdist: distclean MANIFEST.in
 register: distclean MANIFEST.in
 	$(PYTHON) setup.py sdist upload register
 
-WEBDIR=$$HOME/Site/unixuser.org/python/$(PACKAGE)
+WEBDIR=$$HOME/work/Site/unixuser.org/python/$(PACKAGE)
 publish:
 	$(CP) docs/*.html docs/*.png docs/*.css $(WEBDIR)
 
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..8a2cef0
--- /dev/null
+++ b/README.md
@@ -0,0 +1,62 @@
+## PDFMiner
+
+PDFMiner is a tool for extracting information from PDF documents.
+Unlike other PDF-related tools, it focuses entirely on getting 
+and analyzing text data. PDFMiner allows one to obtain
+the exact location of text in a page, as well as 
+other information such as fonts or lines.
+It includes a PDF converter that can transform PDF files
+into other text formats (such as HTML). It has an extensible
+PDF parser that can be used for other purposes than text analysis.
+
+
+** Features **
+
+ * Written entirely in Python.
+ * Parse, analyze, and convert PDF documents.
+ * PDF-1.7 specification support. (well, almost)
+ * CJK languages and vertical writing scripts support.
+ * Various font types (Type1, TrueType, Type3, and CID) support.
+ * Basic encryption (RC4) support.
+ * Outline (TOC) extraction.
+ * Tagged contents extraction.
+ * Automatic layout analysis.
+
+
+** How to Install **
+
+ * Install Python 2.4 or newer. (**Python 3 is not supported.**)
+ * Download the source code.
+ * Unpack it.
+ * Run `setup.py`:
+
+   $ python setup.py install
+
+ * Do the following test:
+
+   $ pdf2txt.py samples/simple1.pdf
+
+
+** For CJK Languages **
+
+In order to process CJK languages, do the following before
+running setup.py install:
+
+  $ make cmap
+  python tools/conv_cmap.py pdfminer/cmap Adobe-CNS1 cmaprsrc/cid2code_Adobe_CNS1.txt
+  reading 'cmaprsrc/cid2code_Adobe_CNS1.txt'...
+  writing 'CNS1_H.py'...
+  ...
+  $ python setup.py install
+
+On Windows machines which don't have <code>make</code> command, 
+paste the following commands on a command line prompt:
+
+  mkdir pdfminer\cmap
+  python tools\conv_cmap.py -c B5=cp950 -c UniCNS-UTF8=utf-8 pdfminer\cmap Adobe-CNS1 cmaprsrc\cid2code_Adobe_CNS1.txt
+  python tools\conv_cmap.py -c GBK-EUC=cp936 -c UniGB-UTF8=utf-8 pdfminer\cmap Adobe-GB1 cmaprsrc\cid2code_Adobe_GB1.txt
+  python tools\conv_cmap.py -c RKSJ=cp932 -c EUC=euc-jp -c UniJIS-UTF8=utf-8 pdfminer\cmap Adobe-Japan1 cmaprsrc\cid2code_Adobe_Japan1.txt
+  python tools\conv_cmap.py -c KSC-EUC=euc-kr -c KSC-Johab=johab -c KSCms-UHC=cp949 -c UniKS-UTF8=utf-8 pdfminer\cmap Adobe-Korea1 cmaprsrc\cid2code_Adobe_Korea1.txt
+  python setup.py install
+
+
diff --git a/README.txt b/README.txt
deleted file mode 100644
index f12c801..0000000
--- a/README.txt
+++ /dev/null
@@ -1 +0,0 @@
-See docs/index.html
diff --git a/docs/index.html b/docs/index.html
index f7d292e..9ce96e1 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -9,7 +9,7 @@
 
 <div align=right class=lastmod>
 <!-- hhmts start -->
-Last Modified: Tue Oct 22 13:19:10 UTC 2013
+Last Modified: Tue Oct 22 15:16:49 UTC 2013
 <!-- hhmts end -->
 </div>
 
@@ -139,7 +139,7 @@ In order to process CJK languages, you need an additional step to take
 during installation:
 <blockquote><pre>
 # <strong>make cmap</strong>
-python tools/conv_cmap.py pdfminer/cmap Adobe-CNS1 cmaprsrc/cid2code_Adobe_CNS1.txt cp950 big5
+python tools/conv_cmap.py pdfminer/cmap Adobe-CNS1 cmaprsrc/cid2code_Adobe_CNS1.txt
 reading 'cmaprsrc/cid2code_Adobe_CNS1.txt'...
 writing 'CNS1_H.py'...
 ...