pdf2json 0.1.0

data/pdf2json-0.52-source/doc/xpdfrc.5

@@ -0,0 +1,480 @@
+.\" Copyright 2002-2005 Glyph & Cog, LLC
+.TH xpdfrc 5 "17 August 2005"
+.SH NAME
+xpdfrc \- configuration file for Xpdf tools (version 3.01)
+.SH DESCRIPTION
+All of the Xpdf tools read a single configuration file.  If you have a
+.I .xpdfrc
+file in your home directory, it will be read.  Otherwise, a
+system-wide configuration file will be read from
+.IR /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
+.I xpdfrc
+file should be placed in the same directory as the executables.
+.PP
+The xpdfrc file consists of a series of configuration options, one
+per line.  Blank lines and lines starting with a \'#' (comments) are
+ignored.
+.PP
+The following sections list all of the configuration options, sorted
+into functional groups.  There is an examples section at the end.
+.SH INCLUDE FILES
+.TP
+.BI include " config\-file"
+Includes the specified config file.  The effect of this is equivalent
+to inserting the contents of
+.I config\-file
+directly into the parent config file in place of the
+.I include
+command.  Config files can be nested arbitrarily deeply.
+.SH CHARACTER MAPPING
+.TP
+.BI 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:
+
+.I "    " hex\-string name
+
+The
+.I hex\-string
+is the Unicode (UCS-2) character index, and
+.I 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.
+.TP
+.BI 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:
+
+.I "    " hex\-string
+
+The
+.I 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 specified file is used.  There are no built-in
+cidToUnicode mappings.
+.TP
+.BI 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
+.IR font\-name\-substring .
+Each line of a unicodeToUnicode file represents one Unicode character:
+
+.RI "    " in\-hex " " out\-hex1 " " out\-hex2 " ..."
+
+The
+.I 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
+.I in\-hex
+will be converted to the specified output sequence.
+.TP
+.BI unicodeMap " encoding\-name map\-file"
+Specifies the file with mapping from Unicode to
+.IR encoding\-name .
+These encodings are used for X display 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:
+.nf
+
+.I "    " in\-start\-hex in\-end\-hex out\-start\-hex
+
+.fi
+Entries for single characters can be abbreviated to:
+.nf
+
+.I "    " in\-hex out\-hex
+
+.fi
+The
+.I in\-start\-hex
+and
+.I in\-end\-hex
+fields (or the single
+.I in\-hex
+field) specify the Unicode range.  The
+.I out\-start\-hex
+field (or the
+.I out\-hex
+field) specifies the start of the output encoding range.  The length
+of the
+.I out\-start\-hex
+(or
+.IR 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 specified file is used.  The
+.IR Latin1 ,
+.IR ASCII7 ,
+.IR Symbol ,
+.IR ZapfDingbats ,
+.IR UTF-8 ,
+and
+.I UCS-2
+encodings are predefined.
+.TP
+.BI cMapDir " registry\-ordering dir"
+Specifies a search directory,
+.IR dir ,
+for CMaps for the
+.I registry\-ordering
+character collection.  There can be multiple directories for a
+particular collection.  There are no default CMap directories.
+.TP
+.BI toUnicodeDir " dir"
+Specifies a search directory,
+.IR dir ,
+for ToUnicode CMaps.  There can be multiple ToUnicode directories.
+There are no default ToUnicode directories.
+.SH DISPLAY FONTS
+.TP
+.BI displayFontT1 " PDF\-font\-name T1\-file"
+Maps a PDF font,
+.IR PDF\-font\-name ,
+to a Type 1 font for display.  The Type 1 font file,
+.IR T1\-file ,
+should be a standard .pfa or .pfb file.
+.TP
+.BI displayFontTT " PDF\-font\-name TT\-file"
+Maps a PDF font,
+.IR PDF\-font\-name ,
+to a TrueType font for display.  The TrueType font file,
+.IR TT\-file ,
+should be a standard .ttf file.
+.TP
+.BI displayNamedCIDFontT1 " PDF\-font\-name T1\-file"
+Maps a specific PDF CID (16-bit) font,
+.IR PDF\-font\-name ,
+to a CID font (16-bit PostScript font), for display.  There are no
+default CID font mappings.
+.TP
+.BI displayCIDFontT1 " registry\-ordering T1\-file"
+Maps the
+.I 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.
+.TP
+.BI displayNamedCIDFontTT " PDF\-font\-name TT\-file"
+Maps a specific PDF CID (16-bit) font,
+.IR PDF\-font\-name ,
+to a (16-bit) TrueType font, for display.  There are no default CID
+font mappings.
+.TP
+.BI displayCIDFontTT " registry\-ordering TT\-file"
+Maps the
+.I registry\-ordering
+character collection to a (16-bit) TrueType 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.
+.TP
+.BI 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 generated 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.
+.SH POSTSCRIPT CONTROL
+.TP
+.BI psPaperSize " width(pts) height(pts)"
+Sets the paper size for PostScript output.  The
+.I width
+and
+.I height
+parameters give the paper size in PostScript points (1 point = 1/72
+inch).
+.TP
+.BR 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.
+.TP
+.BR 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.
+.TP
+.BR 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".
+.TP
+.BR 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".
+.TP
+.BR 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".
+.TP
+.BR 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 imageable area.  This
+defaults to "yes".
+.TP
+.BR 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".
+.TP
+.BR psLevel " level1 | level1sep | level2 | level2sep | level3 | level3Sep"
+Sets the PostScript level to generate.  This defaults to "level2".
+.TP
+.BI psFont " PDF\-font\-name PS\-font\-name"
+When the
+.I PDF\-font\-name
+font is used in a PDF file, it will be translated to the PostScript
+font
+.IR PS\-font\-name ,
+which is assumed to be resident in the printer.  Typically,
+.I PDF\-font\-name
+and
+.I PS\-font\-name
+are the same.  By default, only the Base-14 fonts are assumed to be
+resident.
+.TP
+.BI psNamedFont16 " PDF\-font\-name wMode PS\-font\-name encoding"
+When the 16-bit font
+.I PDF\-font\-name
+is used in a PDF file with the
+.I wMode
+writing mode and is not embedded, the
+.I PS\-font\-name
+font is substituted for it.  The writing mode must be either \'H' for
+horizontal or \'V' for vertical.  The
+.I 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).
+.TP
+.BI psFont16 " registry\-ordering wMode PS\-font\-name encoding"
+When a 16-bit font using the
+.I registry\-ordering
+character collection and 
+.I wMode
+writing mode is not embedded and does not match any of the fonts
+declared in psNamedFont16 commands, the
+.I PS\-font\-name
+font is substituted for it.  The writing mode must be either \'H' for
+horizontal or \'V' for vertical.  The
+.I 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).
+.TP
+.BR psEmbedType1Fonts " yes | no"
+If set to "no", prevents embedding of Type 1 fonts in generated
+PostScript.  This defaults to "yes".
+.TP
+.BR psEmbedTrueTypeFonts " yes | no"
+If set to "no", prevents embedding of TrueType fonts in generated
+PostScript.  This defaults to "yes".
+.TP
+.BR 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.
+.TP
+.BR 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.
+.TP
+.BR psOPI " yes | no"
+If set to "yes", generates PostScript OPI comments for all images and
+forms which have OPI information.  This option is only available if
+the Xpdf tools were compiled with OPI support.  This defaults to "no".
+.TP
+.BR psASCIIHex " yes | no"
+If set to "yes", the ASCIIHexEncode filter will be used instead of
+ASCII85Encode for binary data.  This defaults to "no".
+.TP
+.BI 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 command 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.
+.TP
+.BI fontDir " dir"
+See the description above, in the DISPLAY FONTS section.
+.SH TEXT CONTROL
+.TP
+.BI textEncoding " encoding\-name"
+Sets the encoding to use for text output.  (This can be overridden
+with the "-enc" switch on the command line.)  The
+.I encoding\-name
+must be defined with the unicodeMap command (see above).  This
+defaults to "Latin1".
+.TP
+.BR textEOL " unix | dos | mac"
+Sets the end-of-line convention to use for text output.  The options
+are:
+.nf
+
+    unix = LF
+    dos  = CR+LF
+    mac  = CR
+
+.fi
+(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.
+.TP
+.BR textPageBreaks " yes | no"
+If set to "yes", text extraction will insert page breaks (form feed
+characters) between pages.  This defaults to "yes".
+.TP
+.BR 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".
+.SH MISCELLANEOUS SETTINGS
+.TP
+.BR initialZoom " \fIpercentage\fR | 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 window
+width.
+.TP
+.BR 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".
+.TP
+.BR 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
+"freetypeControl" option.)  This option defaults to "yes".
+.TP
+.BR antialias " yes | no"
+Enables or disables font anti-aliasing in the PDF rasterizer.  This
+option affects all font rasterizers.  ("antialias" replaces the
+anti-aliasing control provided by the old "t1libControl" and
+"freetypeControl" options.)  This default to "yes".
+.TP
+.BI 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.
+.TP
+.BI 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.
+.TP
+.BI 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".
+.TP
+.BI printCommands " yes | no"
+If set to "yes", drawing commands are printed as they're executed
+(useful for debugging).  This defaults to "no".
+.TP
+.BI errQuiet " yes | no"
+If set to "yes", this suppresses all error and warning messages from
+all of the Xpdf tools.  This defaults to "no".
+.SH EXAMPLES
+The following is a sample xpdfrc file.
+.nf
+
+# 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)'"
+
+.fi
+.SH FILES
+.TP
+.B /usr/local/etc/xpdfrc
+This is the default location for the system-wide configuration file.
+Depending on build options, it may be placed elsewhere.
+.TP
+.B $HOME/.xpdfrc
+This is the user's configuration file.  If it exists, it will be read
+in place of the system-wide file.
+.SH AUTHOR
+The Xpdf software and documentation are copyright 1996-2005 Glyph &
+Cog, LLC.
+.SH "SEE ALSO"
+.BR xpdf (1),
+.BR pdftops (1),
+.BR pdftotext (1),
+.BR pdfinfo (1),
+.BR pdftoppm (1),
+.BR pdfimages (1)
+.br
+.B http://www.foolabs.com/xpdf/