pdf2json 0.1.0

data/pdf2json-0.52-source/doc/xpdfrc.cat

@@ -0,0 +1,474 @@
+xpdfrc(5)                                               xpdfrc(5)
+
+
+
+NAME
+       xpdfrc - configuration file for Xpdf tools (version 3.01)
+
+DESCRIPTION
+       All  of  the  Xpdf tools read a single configuration file.
+       If you have a .xpdfrc file in your home directory, it will
+       be read.  Otherwise, a system-wide configuration file will
+       be read from /usr/local/etc/xpdfrc, if it  exists.   (This
+       is  its  default  location; depending on build options, it
+       may be placed elsewhere.)  On Win32  systems,  the  xpdfrc
+       file  should  be  placed in the same directory as the exe-
+       cutables.
+
+       The xpdfrc file consists  of  a  series  of  configuration
+       options,  one  per  line.   Blank lines and lines starting
+       with a '#' (comments) are ignored.
+
+       The following  sections  list  all  of  the  configuration
+       options, sorted into functional groups.  There is an exam-
+       ples section at the end.
+
+INCLUDE FILES
+       include config-file
+              Includes the specified config file.  The effect  of
+              this  is  equivalent  to  inserting the contents of
+              config-file directly into the parent config file in
+              place  of the include command.  Config files can be
+              nested arbitrarily deeply.
+
+CHARACTER MAPPING
+       nameToUnicode map-file
+              Specifies a file with the  mapping  from  character
+              names to Unicode.  This is used to handle PDF fonts
+              that have valid encodings but no  ToUnicode  entry.
+              Each line of a nameToUnicode file looks like this:
+
+                   hex-string name
+
+              The  hex-string  is  the  Unicode (UCS-2) character
+              index, and  name  is  the  corresponding  character
+              name.  Multiple nameToUnicode files can be used; if
+              a character name is given more than once, the  code
+              in  the  last  specified  file is used.  There is a
+              built-in default nameToUnicode table  with  all  of
+              Adobe's standard character names.
+
+       cidToUnicode registry-ordering map-file
+              Specifies  the file with the mapping from character
+              collection to Unicode.  Each line of a cidToUnicode
+              file represents one character:
+
+                   hex-string
+
+              The  hex-string  is  the  Unicode (UCS-2) index for
+              that character.  The first line  maps  CID  0,  the
+              second line CID 1, etc.  File size is determined by
+              size of the character collection.  Only one file is
+              allowed  per  character collection; the last speci-
+              fied file is used.  There are no built-in cidToUni-
+              code mappings.
+
+       unicodeToUnicode font-name-substring map-file
+              This  is  used  to work around PDF fonts which have
+              incorrect Unicode information.  It specifies a file
+              which  maps  from  the  given  (incorrect)  Unicode
+              indexes to the correct ones.  The mapping  will  be
+              used    for    any   font   whose   name   contains
+              font-name-substring.  Each line of a  unicodeToUni-
+              code file represents one Unicode character:
+
+                  in-hex out-hex1 out-hex2 ...
+
+              The  in-hex  field  is an input (incorrect) Unicode
+              index, and the rest of the fields are one  or  more
+              output  (correct) Unicode indexes.  Each occurrence
+              of in-hex will be converted to the specified output
+              sequence.
+
+       unicodeMap encoding-name map-file
+              Specifies  the  file  with  mapping from Unicode to
+              encoding-name.  These encodings are used for X dis-
+              play  fonts and text output (see below).  Each line
+              of a unicodeMap file represents a range of  one  or
+              more  Unicode  characters  which maps linearly to a
+              range in the output encoding:
+
+                   in-start-hex in-end-hex out-start-hex
+
+              Entries for single characters  can  be  abbreviated
+              to:
+
+                   in-hex out-hex
+
+              The in-start-hex and in-end-hex fields (or the sin-
+              gle in-hex field) specify the Unicode  range.   The
+              out-start-hex  field  (or the out-hex field) speci-
+              fies the start of the output encoding  range.   The
+              length  of  the  out-start-hex  (or out-hex) string
+              determines the  length  of  the  output  characters
+              (e.g.,  UTF-8  uses  different  numbers of bytes to
+              represent characters in different ranges).  Entries
+              must  be  given  in increasing Unicode order.  Only
+              one file is allowed per encoding; the  last  speci-
+              fied  file  is  used.   The Latin1, ASCII7, Symbol,
+              ZapfDingbats, UTF-8, and UCS-2 encodings are prede-
+              fined.
+
+       cMapDir registry-ordering dir
+              Specifies  a  search  directory, dir, for CMaps for
+              the registry-ordering character collection.   There
+              can  be  multiple directories for a particular col-
+              lection.  There are no default CMap directories.
+
+       toUnicodeDir dir
+              Specifies a search directory,  dir,  for  ToUnicode
+              CMaps.   There  can  be multiple ToUnicode directo-
+              ries.  There are no default ToUnicode  directories.
+
+DISPLAY FONTS
+       displayFontT1 PDF-font-name T1-file
+              Maps  a  PDF  font, PDF-font-name, to a Type 1 font
+              for display.  The Type 1 font file, T1-file, should
+              be a standard .pfa or .pfb file.
+
+       displayFontTT PDF-font-name TT-file
+              Maps  a PDF font, PDF-font-name, to a TrueType font
+              for display.   The  TrueType  font  file,  TT-file,
+              should be a standard .ttf file.
+
+       displayNamedCIDFontT1 PDF-font-name T1-file
+              Maps    a   specific   PDF   CID   (16-bit)   font,
+              PDF-font-name, to a  CID  font  (16-bit  PostScript
+              font),  for display.  There are no default CID font
+              mappings.
+
+       displayCIDFontT1 registry-ordering T1-file
+              Maps the registry-ordering character collection  to
+              a  CID  font (16-bit PostScript font), for display.
+              This mapping is used if the font name doesn't match
+              any of the fonts declared with displayNamedCIDFont*
+              commands.  There are no default CID font  mappings.
+
+       displayNamedCIDFontTT PDF-font-name TT-file
+              Maps    a   specific   PDF   CID   (16-bit)   font,
+              PDF-font-name, to a  (16-bit)  TrueType  font,  for
+              display.  There are no default CID font mappings.
+
+       displayCIDFontTT registry-ordering TT-file
+              Maps  the registry-ordering character collection to
+              a (16-bit) TrueType font, for display.   This  map-
+              ping  is used if the font name doesn't match any of
+              the fonts declared with  displayNamedCIDFont*  com-
+              mands.  There are no default CID font mappings.
+
+       fontDir dir
+              Specifies  a  search  directory  for  external font
+              files.  There can be multiple fontDir  directories.
+              If  a  PDF  file  uses a font but doesn't embed it,
+              these directories will be searched for  a  matching
+              font  file.  These fonts are used by both xpdf (for
+              display) and pdftops (for embedding in  the  gener-
+              ated  PostScript).  Type 1 fonts must have a suffix
+              of ".pfa", ".pfb", ".ps",  or  no  suffix  at  all.
+              TrueType  fonts  must  have a ".ttf" suffix.  Other
+              files in these directories will be ignored.   There
+              are no default fontDir directories.
+
+POSTSCRIPT CONTROL
+       psPaperSize width(pts) height(pts)
+              Sets  the  paper  size  for PostScript output.  The
+              width and height parameters give the paper size  in
+              PostScript points (1 point = 1/72 inch).
+
+       psPaperSize letter | legal | A4 | A3 | match
+              Sets  the  paper  size  for  PostScript output to a
+              standard size.  The default paper size is set  when
+              xpdf  and  pdftops are built, typically to "letter"
+              or "A4".  This can also be set  to  "match",  which
+              will set the paper size to match the size specified
+              in the PDF file.
+
+       psImageableArea llx lly urx ury
+              Sets the imageable area for PostScript output.  The
+              four integers are the coordinates of the lower-left
+              and upper-right corners of  the  imageable  region,
+              specified  in  points  (with  the  origin being the
+              lower-left corner of the paper).  This defaults  to
+              the  full  paper  size; the psPaperSize option will
+              reset the imageable area coordinates.
+
+       psCrop yes | no
+              If set to "yes", PostScript output  is  cropped  to
+              the CropBox specified in the PDF file; otherwise no
+              cropping is done.  This defaults to "yes".
+
+       psExpandSmaller yes | no
+              If  set  to  "yes",  PDF  pages  smaller  than  the
+              PostScript  imageable area are expanded to fill the
+              imageable area.  Otherwise, no scalling is done  on
+              smaller pages.  This defaults to "no".
+
+       psShrinkLarger yes | no
+              If set to yes, PDF pages larger than the PostScript
+              imageable area are  shrunk  to  fit  the  imageable
+              area.   Otherwise,  no  scaling  is  done on larger
+              pages.  This defaults to "yes".
+
+       psCenter yes | no
+              If  set  to  yes,  PDF  pages  smaller   than   the
+              PostScript  imageable  area (after any scaling) are
+              centered in the imageable  area.   Otherwise,  they
+              are  aligned at the lower-left corner of the image-
+              able area.  This defaults to "yes".
+
+       psDuplex yes | no
+              If set to "yes", the generated PostScript will  set
+              the  "Duplex" pagedevice entry.  This tells duplex-
+              capable  printers  to   enable   duplexing.    This
+              defaults to "no".
+
+       psLevel level1 | level1sep | level2 | level2sep | level3 |
+       level3Sep
+              Sets   the  PostScript  level  to  generate.   This
+              defaults to "level2".
+
+       psFont PDF-font-name PS-font-name
+              When the PDF-font-name font is used in a PDF  file,
+              it  will  be  translated  to  the  PostScript  font
+              PS-font-name, which is assumed to  be  resident  in
+              the    printer.    Typically,   PDF-font-name   and
+              PS-font-name are the same.  By  default,  only  the
+              Base-14 fonts are assumed to be resident.
+
+       psNamedFont16 PDF-font-name wMode PS-font-name encoding
+              When the 16-bit font PDF-font-name is used in a PDF
+              file with the wMode writing mode and is not  embed-
+              ded,  the  PS-font-name font is substituted for it.
+              The writing mode must be either 'H' for  horizontal
+              or  'V'  for  vertical.   The  PS-font-name font is
+              assumed to be resident in the printer  and  to  use
+              the   specified  encoding  (which  must  have  been
+              defined with the unicodeMap command).
+
+       psFont16 registry-ordering wMode PS-font-name encoding
+              When a  16-bit  font  using  the  registry-ordering
+              character  collection and wMode writing mode is not
+              embedded and  does  not  match  any  of  the  fonts
+              declared    in    psNamedFont16    commands,    the
+              PS-font-name font is substituted for it.  The writ-
+              ing  mode  must be either 'H' for horizontal or 'V'
+              for vertical.  The PS-font-name font is assumed  to
+              be resident in the printer and to use the specified
+              writing mode and encoding  (which  must  have  been
+              defined with the unicodeMap command).
+
+       psEmbedType1Fonts yes | no
+              If  set to "no", prevents embedding of Type 1 fonts
+              in generated PostScript.  This defaults to "yes".
+
+       psEmbedTrueTypeFonts yes | no
+              If set to  "no",  prevents  embedding  of  TrueType
+              fonts  in  generated  PostScript.  This defaults to
+              "yes".
+
+       psEmbedCIDTrueTypeFonts yes | no
+              If set to "no", prevents embedding of CID  TrueType
+              fonts   in   generated  PostScript.   For  Level  3
+              PostScript, this generates a CID  font,  for  lower
+              levels it generates a non-CID composite font.
+
+       psEmbedCIDPostScriptFonts yes | no
+              If   set   to   "no",  prevents  embedding  of  CID
+              PostScript  fonts  in  generated  PostScript.   For
+              Level  3 PostScript, this generates a CID font, for
+              lower levels it generates a non-CID composite font.
+
+       psOPI yes | no
+              If  set to "yes", generates PostScript OPI comments
+              for all images and forms which  have  OPI  informa-
+              tion.   This  option  is only available if the Xpdf
+              tools  were  compiled  with  OPI   support.    This
+              defaults to "no".
+
+       psASCIIHex yes | no
+              If  set to "yes", the ASCIIHexEncode filter will be
+              used instead  of  ASCII85Encode  for  binary  data.
+              This defaults to "no".
+
+       psFile file-or-command
+              Sets  the  default PostScript file or print command
+              for xpdf.  Commands start  with  a  '|'  character;
+              anything  else is a file.  If the file name or com-
+              mand contains  spaces  it  must  be  quoted.   This
+              defaults  to  unset, which tells xpdf to generate a
+              name  of  the  form  <file>.ps  for  a   PDF   file
+              <file>.pdf.
+
+       fontDir dir
+              See  the  description  above,  in the DISPLAY FONTS
+              section.
+
+TEXT CONTROL
+       textEncoding encoding-name
+              Sets the encoding to use for  text  output.   (This
+              can  be  overridden  with  the "-enc" switch on the
+              command line.)  The encoding-name must  be  defined
+              with  the  unicodeMap  command  (see  above).  This
+              defaults to "Latin1".
+
+       textEOL unix | dos | mac
+              Sets the end-of-line convention  to  use  for  text
+              output.  The options are:
+
+                  unix = LF
+                  dos  = CR+LF
+                  mac  = CR
+
+              (This  can  be overridden with the "-eol" switch on
+              the command line.)  The default value is  based  on
+              the OS where xpdf and pdftotext were built.
+
+       textPageBreaks yes | no
+              If  set  to "yes", text extraction will insert page
+              breaks (form feed characters) between pages.   This
+              defaults to "yes".
+
+       textKeepTinyChars yes | no
+              If  set  to  "yes",  text  extraction will keep all
+              characters.  If set to "no", text  extraction  will
+              discard  tiny  (smaller  than  3  point) characters
+              after the first 50000 per page, avoiding  extremely
+              slow run times for PDF files that use special fonts
+              to do shading or cross-hatching.  This defaults  to
+              "no".
+
+MISCELLANEOUS SETTINGS
+       initialZoom percentage | page | width
+              Sets the initial zoom factor.  A number specifies a
+              zoom percentage, where 100 means 72 dpi.   You  may
+              also  specify 'page', to fit the page to the window
+              size, or 'width', to fit the page width to the win-
+              dow width.
+
+       enableT1lib yes | no
+              Enables  or  disables  use  of t1lib (a Type 1 font
+              rasterizer).  This is only  relevant  if  the  Xpdf
+              tools    were    built    with    t1lib    support.
+              ("enableT1lib"  replaces  the  old   "t1libControl"
+              option.)  This option defaults to "yes".
+
+       enableFreeType yes | no
+              Enables  or  disables use of FreeType (a TrueType /
+              Type 1 font rasterizer).  This is only relevant  if
+              the  Xpdf  tools  were built with FreeType support.
+              ("enableFreeType" replaces  the  old  "freetypeCon-
+              trol" option.)  This option defaults to "yes".
+
+       antialias yes | no
+              Enables  or  disables font anti-aliasing in the PDF
+              rasterizer.  This option affects all font rasteriz-
+              ers.   ("antialias" replaces the anti-aliasing con-
+              trol  provided  by  the  old   "t1libControl"   and
+              "freetypeControl" options.)  This default to "yes".
+
+       urlCommand command
+              Sets the command executed when you click on  a  URL
+              link.   The  string  "%s" will be replaced with the
+              URL.  (See the example below.)  This has no default
+              value.
+
+       movieCommand command
+              Sets the command executed when you click on a movie
+              annotation.  The string "%s" will be replaced  with
+              the movie file name.  This has no default value.
+
+       mapNumericCharNames yes | no
+              If set to "yes", the Xpdf tools will attempt to map
+              various numeric character names sometimes  used  in
+              font  subsets.   In some cases this leads to usable
+              text, and in other cases it leads to  gibberish  --
+              there is no way for Xpdf to tell.  This defaults to
+              "yes".
+
+       printCommands yes | no
+              If set to "yes", drawing commands  are  printed  as
+              they're  executed  (useful  for  debugging).   This
+              defaults to "no".
+
+       errQuiet yes | no
+              If set to "yes",  this  suppresses  all  error  and
+              warning  messages from all of the Xpdf tools.  This
+              defaults to "no".
+
+EXAMPLES
+       The following is a sample xpdfrc file.
+
+       # from the Thai support package
+       nameToUnicode /usr/local/share/xpdf/Thai.nameToUnicode
+
+       # from the Japanese support package
+       cidToUnicode Adobe-Japan1 /usr/local/share/xpdf/Adobe-Japan1.cidToUnicode
+       unicodeMap   JISX0208     /usr/local/share/xpdf/JISX0208.unicodeMap
+       cMapDir      Adobe-Japan1 /usr/local/share/xpdf/cmap/Adobe-Japan1
+
+       # use the Base-14 Type 1 fonts from ghostscript
+       displayFontT1 Times-Roman           /usr/local/share/ghostscript/fonts/n021003l.pfb
+       displayFontT1 Times-Italic          /usr/local/share/ghostscript/fonts/n021023l.pfb
+       displayFontT1 Times-Bold            /usr/local/share/ghostscript/fonts/n021004l.pfb
+       displayFontT1 Times-BoldItalic      /usr/local/share/ghostscript/fonts/n021024l.pfb
+       displayFontT1 Helvetica             /usr/local/share/ghostscript/fonts/n019003l.pfb
+       displayFontT1 Helvetica-Oblique     /usr/local/share/ghostscript/fonts/n019023l.pfb
+       displayFontT1 Helvetica-Bold        /usr/local/share/ghostscript/fonts/n019004l.pfb
+       displayFontT1 Helvetica-BoldOblique /usr/local/share/ghostscript/fonts/n019024l.pfb
+       displayFontT1 Courier               /usr/local/share/ghostscript/fonts/n022003l.pfb
+       displayFontT1 Courier-Oblique       /usr/local/share/ghostscript/fonts/n022023l.pfb
+       displayFontT1 Courier-Bold          /usr/local/share/ghostscript/fonts/n022004l.pfb
+       displayFontT1 Courier-BoldOblique   /usr/local/share/ghostscript/fonts/n022024l.pfb
+       displayFontT1 Symbol                /usr/local/share/ghostscript/fonts/s050000l.pfb
+       displayFontT1 ZapfDingbats          /usr/local/share/ghostscript/fonts/d050000l.pfb
+
+       # use the Bakoma Type 1 fonts
+       # (this assumes they happen to be installed in /usr/local/fonts/bakoma)
+       fontDir /usr/local/fonts/bakoma
+
+       # set some PostScript options
+       psPaperSize          letter
+       psDuplex             no
+       psLevel              level2
+       psEmbedType1Fonts    yes
+       psEmbedTrueTypeFonts yes
+       psFile               "| lpr -Pprinter5"
+
+       # assume that the PostScript printer has the Univers and
+       # Univers-Bold fonts
+       psFont Univers      Univers
+       psFont Univers-Bold Univers-Bold
+
+       # set the text output options
+       textEncoding UTF-8
+       textEOL      unix
+
+       # misc options
+       t1libControl    low
+       freetypeControl low
+       urlCommand      "netscape -remote 'openURL(%s)'"
+
+
+FILES
+       /usr/local/etc/xpdfrc
+              This is the default location  for  the  system-wide
+              configuration file.  Depending on build options, it
+              may be placed elsewhere.
+
+       $HOME/.xpdfrc
+              This is  the  user's  configuration  file.   If  it
+              exists, it will be read in place of the system-wide
+              file.
+
+AUTHOR
+       The  Xpdf  software  and   documentation   are   copyright
+       1996-2005 Glyph & Cog, LLC.
+
+SEE ALSO
+       xpdf(1),     pdftops(1),     pdftotext(1),     pdfinfo(1),
+       pdftoppm(1), pdfimages(1)
+       http://www.foolabs.com/xpdf/
+
+
+
+                          17 August 2005                xpdfrc(5)