From 537fca97233cb80a14a76752e2cde2aa06eeda4e Mon Sep 17 00:00:00 2001 From: miwi Date: Sat, 28 Jul 2018 12:05:28 +0000 Subject: PDFMiner.six is a fork of PDFMiner using six for Python 2 + 3 compatibility. 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: - 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. WWW: https://github.com/pdfminer/pdfminer.six PR: 229447 Submitted by: freebsd_ports@k-worx.org Sponsored by: iXsystems Inc. --- textproc/Makefile | 1 + textproc/py-pdfminer.six/Makefile | 32 ++++++++++++++++++++++++++++++++ textproc/py-pdfminer.six/distinfo | 3 +++ textproc/py-pdfminer.six/pkg-descr | 22 ++++++++++++++++++++++ 4 files changed, 58 insertions(+) create mode 100644 textproc/py-pdfminer.six/Makefile create mode 100644 textproc/py-pdfminer.six/distinfo create mode 100644 textproc/py-pdfminer.six/pkg-descr (limited to 'textproc') diff --git a/textproc/Makefile b/textproc/Makefile index de8aa7c679df..1f447c849b3d 100644 --- a/textproc/Makefile +++ b/textproc/Makefile @@ -1340,6 +1340,7 @@ SUBDIR += py-parsimonious SUBDIR += py-parso SUBDIR += py-pdfminer + SUBDIR += py-pdfminer.six SUBDIR += py-pdfminer3k SUBDIR += py-pdfrw SUBDIR += py-pss diff --git a/textproc/py-pdfminer.six/Makefile b/textproc/py-pdfminer.six/Makefile new file mode 100644 index 000000000000..2b779bf64de5 --- /dev/null +++ b/textproc/py-pdfminer.six/Makefile @@ -0,0 +1,32 @@ +# $FreeBSD$ + +PORTNAME= pdfminer.six +PORTVERSION= 20170720 +CATEGORIES= textproc python +MASTER_SITES= CHEESESHOP +PKGNAMEPREFIX= ${PYTHON_PKGNAMEPREFIX} + +MAINTAINER= freebsd_ports@k-worx.org +COMMENT= PDF parser and analyzer + +LICENSE= MIT +LICENSE_FILE= ${WRKSRC}/LICENSE + +RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}six>=0:devel/py-six@${PY_FLAVOR} \ + ${PYTHON_PKGNAMEPREFIX}pycryptodome>=0:security/py-pycryptodome@${PY_FLAVOR} + +USES= python shebangfix dos2unix +USE_PYTHON= distutils concurrent autoplist +SHEBANG_FILES= tools/dumppdf.py tools/pdf2txt.py tools/latin2ascii.py +DOS2UNIXGLOB= *.py + +CONFLICTS_INSTALL= py??-pdfminer-* py??-pdfminer3k-* +NO_ARCH= yes + +.include + +.if ${PYTHON_REL} >= 3000 +RUN_DEPENDS+= ${PYTHON_PKGNAMEPREFIX}chardet>=0:textproc/py-chardet@${PY_FLAVOR} +.endif + +.include diff --git a/textproc/py-pdfminer.six/distinfo b/textproc/py-pdfminer.six/distinfo new file mode 100644 index 000000000000..f1ab6eeda2fc --- /dev/null +++ b/textproc/py-pdfminer.six/distinfo @@ -0,0 +1,3 @@ +TIMESTAMP = 1530196324 +SHA256 (pdfminer.six-20170720.tar.gz) = a37c6348a8d903cf5f7d50346b0569a7c669afdb625b1ee25056f01fb82bd3e0 +SIZE (pdfminer.six-20170720.tar.gz) = 11992116 diff --git a/textproc/py-pdfminer.six/pkg-descr b/textproc/py-pdfminer.six/pkg-descr new file mode 100644 index 000000000000..5061956d85d0 --- /dev/null +++ b/textproc/py-pdfminer.six/pkg-descr @@ -0,0 +1,22 @@ +PDFMiner.six is a fork of PDFMiner using six for Python 2 + 3 compatibility. + +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: + +- 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. + +WWW: https://github.com/pdfminer/pdfminer.six -- cgit