|
Link Here
|
| 1 |
PORTNAME= textract |
| 2 |
PORTVERSION= 1.6.5 |
| 3 |
CATEGORIES= textproc python |
| 4 |
MASTER_SITES= CHEESESHOP |
| 5 |
PKGNAMEPREFIX= ${PYTHON_PKGNAMEPREFIX} |
| 6 |
|
| 7 |
MAINTAINER= DtxdF@riseup.net |
| 8 |
COMMENT= Extract text from any document |
| 9 |
|
| 10 |
LICENSE= MIT |
| 11 |
LICENSE_FILE= ${WRKSRC}/LICENSE |
| 12 |
|
| 13 |
RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}argcomplete>=1.10.0:devel/py-argcomplete@${PY_FLAVOR} \ |
| 14 |
${PYTHON_PKGNAMEPREFIX}chardet>=3:textproc/py-chardet@${PY_FLAVOR} \ |
| 15 |
${PYTHON_PKGNAMEPREFIX}six>1.12.0:devel/py-six@${PY_FLAVOR} |
| 16 |
|
| 17 |
USES= python:3.8+ |
| 18 |
USE_PYTHON= autoplist distutils |
| 19 |
|
| 20 |
OPTIONS_DEFINE= ANTIWORD BEAUTIFULSOUP DOCX2TXT MSG LIBXML2 \ |
| 21 |
LIBXSLT PPTX PS SPREADSHEET UNRTF |
| 22 |
OPTIONS_DEFAULT= ANTIWORD BEAUTIFULSOUP DOCX2TXT FFMPEG FLAC JPEG_TURBO \ |
| 23 |
LAME LIBXML2 LIBXSLT MSG PDFTOTEXT PPTX PS SOX \ |
| 24 |
SPEECH_RECOGNITION SPREADSHEET TESSERACT UNRTF |
| 25 |
|
| 26 |
ANTIWORD_DESC= DOC document support |
| 27 |
DOCX2TXT_DESC= DOCX document support |
| 28 |
BEAUTIFULSOUP_DESC= HTML parsing library |
| 29 |
TESSERACT_DESC= Commercial quality open source OCR engine |
| 30 |
JPEG_TURBO_DESC= SIMD-accelerated JPEG codec |
| 31 |
SOX_DESC= Command-line audio processing tool |
| 32 |
SPEECH_RECOGNITION_DESC= Python library for performing speech recognition |
| 33 |
POCKETSPHINX_DESC= Interface to CMU Sphinxbase and Pocketsphinx |
| 34 |
SPREADSHEET_DESC= XLS and XLSX spreadsheet support |
| 35 |
UNRTF_DESC= RTF document support |
| 36 |
PDFTOTEXT_DESC= Extract text from a PDF document |
| 37 |
PDFMINER_DESC= PDF parser and analyzer |
| 38 |
MSG_DESC= MS Outlook MSG file format support |
| 39 |
PPTX_DESC= MS PowerPoint PPTX presentations support |
| 40 |
LIBXML2_DESC= Python interface for XML parser library |
| 41 |
LIBXSLT_DESC= XML stylesheet transformation library |
| 42 |
|
| 43 |
# DOC |
| 44 |
ANTIWORD_RUN_DEPENDS= antiword>0:textproc/antiword |
| 45 |
# DOCX |
| 46 |
DOCX2TXT_RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}docx2txt>=0.8:textproc/py-docx2txt@${PY_FLAVOR} |
| 47 |
# HTML, EPUB, etc. |
| 48 |
BEAUTIFULSOUP_RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}beautifulsoup>=4.8.0:www/py-beautifulsoup@${PY_FLAVOR} |
| 49 |
# OCR |
| 50 |
TESSERACT_RUN_DEPENDS= tesseract>0:graphics/tesseract |
| 51 |
JPEG_TURBO_RUN_DEPENDS= jpeg-turbo>0:graphics/jpeg-turbo |
| 52 |
# AUDIO |
| 53 |
SOX_RUN_DEPENDS= sox>0:audio/sox |
| 54 |
FFMPEG_RUN_DEPENDS= ffmpeg>0:multimedia/ffmpeg |
| 55 |
FLAC_RUN_DEPENDS= flac>0:audio/flac |
| 56 |
LAME_RUN_DEPENDS= lame>0:audio/lame |
| 57 |
SPEECH_RECOGNITION_RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}SpeechRecognition>=3.8.1:audio/py-speechrecognition@${PY_FLAVOR} |
| 58 |
POCKETSPHINX_RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}pocketsphinx>0:audio/py-pocketsphinx@${PY_FLAVOR} |
| 59 |
# XLS and XLSX |
| 60 |
SPREADSHEET_RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}xlrd>=1.2.0:textproc/py-xlrd@${PY_FLAVOR} |
| 61 |
# RTF |
| 62 |
UNRTF_RUN_DEPENDS= unrtf>0:textproc/unrtf |
| 63 |
# PDF |
| 64 |
PDFTOTEXT_RUN_DEPENDS= poppler-utils>0:graphics/poppler-utils |
| 65 |
PDFMINER_RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}pdfminer.six>=20191110:textproc/py-pdfminer.six@${PY_FLAVOR} |
| 66 |
# PS |
| 67 |
PS_RUN_DEPENDS= pstotext>0:print/pstotext |
| 68 |
# MSG |
| 69 |
MSG_RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}extract-msg>=0.29:textproc/py-extract-msg@${PY_FLAVOR} |
| 70 |
# PPTX |
| 71 |
PPTX_RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}python-pptx>=0.6.18:textproc/py-python-pptx@${PY_FLAVOR} |
| 72 |
# MISC |
| 73 |
LIBXML2_RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}libxml2>0:textproc/py-libxml2@${PY_FLAVOR} |
| 74 |
LIBXSLT_RUN_DEPENDS= libxslt>=1.1.15:textproc/libxslt |
| 75 |
|
| 76 |
OPTIONS_GROUP= AUDIO OCR PDF RTF |
| 77 |
OPTIONS_GROUP_AUDIO= FFMPEG FLAC LAME POCKETSPHINX SOX SPEECH_RECOGNITION |
| 78 |
OPTIONS_GROUP_OCR= JPEG_TURBO TESSERACT |
| 79 |
OPTIONS_GROUP_PDF= PDFMINER PDFTOTEXT |
| 80 |
|
| 81 |
.include <bsd.port.mk> |