zacc806
/
pdfminer.six
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Cleanup imports. Use relative imports.

pull/1/head
Yusuke Shinyama 2014-06-26 18:12:39 +09:00
parent 2e900e5d10
commit 8791355e1d
16 changed files with 162 additions and 103 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Makefile
View File

@ -61,6 +61,6 @@ test: cmap
pdfminer/ascii85.py \
pdfminer/runlength.py \
pdfminer/rijndael.py
$(PYTHON) pdfminer/ccitt.py
$(PYTHON) pdfminer/psparser.py
$(PYTHON) -m pdfminer.ccitt
$(PYTHON) -m pdfminer.psparser
cd samples && $(MAKE) test

14
pdfminer/cmapdb.py
View File

@ -21,12 +21,14 @@ except ImportError:
import pickle as pickle
import struct
import logging
from psparser import PSStackParser
from psparser import PSSyntaxError, PSEOF
from psparser import PSLiteral
from psparser import literal_name
from encodingdb import name2unicode
from utils import choplist, nunpack
from .psparser import PSStackParser
from .psparser import PSSyntaxError
from .psparser import PSEOF
from .psparser import PSLiteral
from .psparser import literal_name
from .encodingdb import name2unicode
from .utils import choplist
from .utils import nunpack
class CMapError(Exception):

27
pdfminer/converter.py
View File

@ -1,14 +1,25 @@
#!/usr/bin/env python
import sys
import logging
import re
from pdfdevice import PDFTextDevice
from pdffont import PDFUnicodeNotDefined
from layout import LTContainer, LTPage, LTText, LTLine, LTRect, LTCurve
from layout import LTFigure, LTImage, LTChar, LTTextLine
from layout import LTTextBox, LTTextBoxVertical, LTTextGroup
from utils import apply_matrix_pt, mult_matrix
from utils import enc, bbox2str
from .pdfdevice import PDFTextDevice
from .pdffont import PDFUnicodeNotDefined
from .layout import LTContainer
from .layout import LTPage
from .layout import LTText
from .layout import LTLine
from .layout import LTRect
from .layout import LTCurve
from .layout import LTFigure
from .layout import LTImage
from .layout import LTChar
from .layout import LTTextLine
from .layout import LTTextBox
from .layout import LTTextBoxVertical
from .layout import LTTextGroup
from .utils import apply_matrix_pt
from .utils import mult_matrix
from .utils import enc
from .utils import bbox2str
## PDFLayoutAnalyzer

7
pdfminer/encodingdb.py
View File

@ -1,9 +1,8 @@
#!/usr/bin/env python
import re
from psparser import PSLiteral
from glyphlist import glyphname2unicode
from latin_enc import ENCODING
from .psparser import PSLiteral
from .glyphlist import glyphname2unicode
from .latin_enc import ENCODING
STRIP_NAME = re.compile(r'[0-9]+')

9
pdfminer/image.py
View File

@ -1,9 +1,12 @@
#!/usr/bin/env python
import struct
import os, os.path
import os
import os.path
from io import BytesIO
from pdftypes import LITERALS_DCT_DECODE
from pdfcolor import LITERAL_DEVICE_GRAY, LITERAL_DEVICE_RGB, LITERAL_DEVICE_CMYK
from .pdftypes import LITERALS_DCT_DECODE
from .pdfcolor import LITERAL_DEVICE_GRAY
from .pdfcolor import LITERAL_DEVICE_RGB
from .pdfcolor import LITERAL_DEVICE_CMYK
def align32(x):

11
pdfminer/layout.py
View File

@ -1,6 +1,13 @@
#!/usr/bin/env python
from utils import INF, Plane, get_bound, uniq, csort, fsplit
from utils import bbox2str, matrix2str, apply_matrix_pt
from .utils import INF
from .utils import Plane
from .utils import get_bound
from .utils import uniq
from .utils import csort
from .utils import fsplit
from .utils import bbox2str
from .utils import matrix2str
from .utils import apply_matrix_pt
## IndexAssigner

2
pdfminer/lzw.py
View File

@ -1,6 +1,4 @@
#!/usr/bin/env python
import sys
import logging
from io import BytesIO

2
pdfminer/pdfcolor.py
View File

@ -1,5 +1,5 @@
#!/usr/bin/env python
from psparser import LIT
from .psparser import LIT
## PDFColorSpace

9
pdfminer/pdfdevice.py
View File

@ -1,7 +1,10 @@
#!/usr/bin/env python
from utils import mult_matrix, translate_matrix
from utils import enc, bbox2str, isnumber
from pdffont import PDFUnicodeNotDefined
from .utils import mult_matrix
from .utils import translate_matrix
from .utils import enc
from .utils import bbox2str
from .utils import isnumber
from .pdffont import PDFUnicodeNotDefined
## PDFDevice

36
pdfminer/pdfdocument.py
View File

@ -1,5 +1,4 @@
#!/usr/bin/env python
import sys
import re
import struct
import logging
@ -13,20 +12,27 @@ try:
from Crypto.Hash import SHA256
except ImportError:
AES = SHA256 = None
import arcfour as ARC4
from psparser import PSEOF
from psparser import literal_name
from psparser import LIT, KWD, STRICT
from pdftypes import PDFException, PDFTypeError, PDFNotImplementedError
from pdftypes import PDFObjectNotFound, PDFStream
from pdftypes import decipher_all
from pdftypes import int_value
from pdftypes import str_value, list_value, dict_value, stream_value
from pdfparser import PDFSyntaxError
from pdfparser import PDFStreamParser
from utils import choplist, nunpack
from utils import decode_text
from . import arcfour as ARC4
from .psparser import PSEOF
from .psparser import literal_name
from .psparser import LIT
from .psparser import KWD
from .psparser import STRICT
from .pdftypes import PDFException
from .pdftypes import PDFTypeError
from .pdftypes import PDFStream
from .pdftypes import PDFObjectNotFound
from .pdftypes import decipher_all
from .pdftypes import int_value
from .pdftypes import str_value
from .pdftypes import list_value
from .pdftypes import dict_value
from .pdftypes import stream_value
from .pdfparser import PDFSyntaxError
from .pdfparser import PDFStreamParser
from .utils import choplist
from .utils import nunpack
from .utils import decode_text
## Exceptions

40
pdfminer/pdffont.py
View File

@ -2,17 +2,31 @@
import sys
import struct
from io import BytesIO
from cmapdb import CMapDB, CMapParser, FileUnicodeMap, CMap
from encodingdb import EncodingDB, name2unicode
from psparser import PSStackParser
from psparser import PSEOF
from psparser import LIT, KWD, STRICT
from psparser import PSLiteral, literal_name
from pdftypes import PDFException, resolve1
from pdftypes import int_value, num_value
from pdftypes import list_value, dict_value, stream_value
from fontmetrics import FONT_METRICS
from utils import apply_matrix_norm, nunpack, choplist, isnumber
from .cmapdb import CMapDB
from .cmapdb import CMapParser
from .cmapdb import FileUnicodeMap
from .cmapdb import CMap
from .encodingdb import EncodingDB
from .encodingdb import name2unicode
from .psparser import PSStackParser
from .psparser import PSEOF
from .psparser import LIT
from .psparser import KWD
from .psparser import STRICT
from .psparser import PSLiteral
from .psparser import literal_name
from .pdftypes import PDFException
from .pdftypes import resolve1
from .pdftypes import int_value
from .pdftypes import num_value
from .pdftypes import list_value
from .pdftypes import dict_value
from .pdftypes import stream_value
from .fontmetrics import FONT_METRICS
from .utils import apply_matrix_norm
from .utils import nunpack
from .utils import choplist
from .utils import isnumber
def get_widths(seq):
@ -566,7 +580,7 @@ class PDFType1Font(PDFSimpleFont):
except KeyError:
descriptor = dict_value(spec.get('FontDescriptor', {}))
firstchar = int_value(spec.get('FirstChar', 0))
lastchar = int_value(spec.get('LastChar', 255))
#lastchar = int_value(spec.get('LastChar', 255))
widths = list_value(spec.get('Widths', [0]*256))
widths = dict((i+firstchar, w) for (i, w) in enumerate(widths))
PDFSimpleFont.__init__(self, descriptor, widths, spec)
@ -595,7 +609,7 @@ class PDFType3Font(PDFSimpleFont):
def __init__(self, rsrcmgr, spec):
firstchar = int_value(spec.get('FirstChar', 0))
lastchar = int_value(spec.get('LastChar', 0))
#lastchar = int_value(spec.get('LastChar', 0))
widths = list_value(spec.get('Widths', [0]*256))
widths = dict((i+firstchar, w) for (i, w) in enumerate(widths))
if 'FontDescriptor' in spec:

46
pdfminer/pdfinterp.py
View File

@ -1,25 +1,35 @@
#!/usr/bin/env python
import sys
import re
import logging
from io import BytesIO
from cmapdb import CMapDB, CMap
from psparser import PSTypeError, PSEOF
from psparser import PSKeyword, literal_name, keyword_name
from psparser import PSStackParser
from psparser import LIT, KWD, STRICT
from pdftypes import PDFException, PDFStream, PDFObjRef
from pdftypes import resolve1
from pdftypes import list_value, dict_value, stream_value
from pdffont import PDFFontError
from pdffont import PDFType1Font, PDFTrueTypeFont, PDFType3Font
from pdffont import PDFCIDFont
from pdfcolor import PDFColorSpace
from pdfcolor import PREDEFINED_COLORSPACE
from pdfcolor import LITERAL_DEVICE_GRAY, LITERAL_DEVICE_RGB
from pdfcolor import LITERAL_DEVICE_CMYK
from utils import choplist
from utils import mult_matrix, MATRIX_IDENTITY
from .cmapdb import CMapDB
from .cmapdb import CMap
from .psparser import PSTypeError
from .psparser import PSEOF
from .psparser import PSKeyword
from .psparser import literal_name
from .psparser import keyword_name
from .psparser import PSStackParser
from .psparser import LIT
from .psparser import KWD
from .psparser import STRICT
from .pdftypes import PDFException
from .pdftypes import PDFStream
from .pdftypes import PDFObjRef
from .pdftypes import resolve1
from .pdftypes import list_value
from .pdftypes import dict_value
from .pdftypes import stream_value
from .pdffont import PDFFontError
from .pdffont import PDFType1Font
from .pdffont import PDFTrueTypeFont
from .pdffont import PDFType3Font
from .pdffont import PDFCIDFont
from .pdfcolor import PDFColorSpace
from .pdfcolor import PREDEFINED_COLORSPACE
from .utils import choplist
from .utils import mult_matrix
from .utils import MATRIX_IDENTITY
## Exceptions

18
pdfminer/pdfpage.py
View File

@ -1,14 +1,14 @@
#!/usr/bin/env python
import sys
import logging
from psparser import LIT
from pdftypes import PDFObjectNotFound
from pdftypes import resolve1
from pdftypes import int_value, list_value, dict_value
from pdfparser import PDFParser
from pdfdocument import PDFDocument
from pdfdocument import PDFEncryptionError
from pdfdocument import PDFTextExtractionNotAllowed
from .psparser import LIT
from .pdftypes import PDFObjectNotFound
from .pdftypes import resolve1
from .pdftypes import int_value
from .pdftypes import list_value
from .pdftypes import dict_value
from .pdfparser import PDFParser
from .pdfdocument import PDFDocument
from .pdfdocument import PDFTextExtractionNotAllowed
# some predefined literals and keywords.
LITERAL_PAGE = LIT('Page')

18
pdfminer/pdfparser.py
View File

@ -1,14 +1,16 @@
#!/usr/bin/env python
import sys
import logging
from io import BytesIO
from psparser import PSStackParser
from psparser import PSSyntaxError, PSEOF
from psparser import KWD, STRICT
from pdftypes import PDFException
from pdftypes import PDFStream, PDFObjRef
from pdftypes import int_value
from pdftypes import dict_value
from .psparser import PSStackParser
from .psparser import PSSyntaxError
from .psparser import PSEOF
from .psparser import KWD
from .psparser import STRICT
from .pdftypes import PDFException
from .pdftypes import PDFStream
from .pdftypes import PDFObjRef
from .pdftypes import int_value
from .pdftypes import dict_value
## Exceptions

19
pdfminer/pdftypes.py
View File

@ -1,12 +1,17 @@
#!/usr/bin/env python
import zlib
from lzw import lzwdecode
from ascii85 import ascii85decode, asciihexdecode
from runlength import rldecode
from ccitt import ccittfaxdecode
from psparser import PSException, PSObject
from psparser import LIT, STRICT
from utils import apply_png_predictor, isnumber
from .lzw import lzwdecode
from .ascii85 import ascii85decode
from .ascii85 import asciihexdecode
from .runlength import rldecode
from .ccitt import ccittfaxdecode
from .psparser import PSException
from .psparser import PSObject
from .psparser import LIT
from .psparser import STRICT
from .utils import apply_png_predictor
from .utils import isnumber
LITERAL_CRYPT = LIT('Crypt')

3
pdfminer/psparser.py
View File

@ -1,8 +1,7 @@
#!/usr/bin/env python
import sys
import re
import logging
from utils import choplist
from .utils import choplist
STRICT = 0