pdf2json 0.1.0

data/pdf2json-0.52-source/doc/pdftotext.hlp

@@ -0,0 +1,133 @@
+! Generated automatically by mantohlp
+1 pdftotext
+
+       pdftotext  -  Portable  Document Format (PDF) to text con-
+       verter
+
+       pdftotext [options] [PDF-file [text-file]]
+
+       Pdftotext converts Portable Document Format (PDF) files to
+       plain text.
+
+       Pdftotext  reads the PDF file, PDF-file, and writes a text
+       file, text-file.  If text-file is not specified, pdftotext
+       converts  file.pdf  to file.txt.  If text-file is '-', the
+       text is sent to stdout.
+
+                                                               ()
+
+2 ONFIGURATION_FIL
+
+       Pdftotext reads a configuration file at startup.  It first
+       tries to find the user's private config  file,  ~/.xpdfrc.
+       If  that  doesn't exist, it looks for a system-wide config
+       file, typically /usr/local/etc/xpdfrc (but  this  location
+       can   be  changed  when  pdftotext  is  built).   See  the
+       xpdfrc(5) man page for details.
+
+                                                               ()
+
+2 OPTIONS
+
+       Many  of  the following options can be set with configura-
+       tion file commands.  These are listed in  square  brackets
+       with  the  description  of  the corresponding command line
+       option.
+
+       -f number
+              Specifies the first page to convert.
+
+       -l number
+              Specifies the last page to convert.
+
+       -layout
+              Maintain (as best as possible) the original  physi-
+              cal  layout  of the text.  The default is to 'undo'
+              physical layout (columns,  hyphenation,  etc.)  and
+              output the text in reading order.
+
+       -raw   Keep  the  text in content stream order.  This is a
+              hack which often "undoes" column  formatting,  etc.
+              Use of raw mode is no longer recommended.
+
+       -htmlmeta
+              Generate  a  simple  HTML  file, including the meta
+              information.  This simply wraps the text  in  <pre>
+              and </pre> and prepends the meta headers.
+
+       -enc encoding-name
+              Sets  the  encoding  to  use  for text output.  The
+              encoding-name must be defined with  the  unicodeMap
+              command  (see  xpdfrc(5)).   The  encoding  name is
+              case-sensitive.  This defaults to  "Latin1"  (which
+              is  a built-in encoding).  [config file: textEncod-
+              ing]
+
+       -eol unix | dos | mac
+              Sets the end-of-line convention  to  use  for  text
+              output.  [config file: textEOL]
+
+       -nopgbrk
+              Don't  insert  page  breaks  (form feed characters)
+              between pages.  [config file: textPageBreaks]
+
+       -opw password
+              Specify the owner password for the PDF file.   Pro-
+              viding  this will bypass all security restrictions.
+
+       -upw password
+              Specify the user password for the PDF file.
+
+       -q     Don't print any messages or errors.  [config  file:
+              errQuiet]
+
+       -cfg config-file
+              Read  config-file in place of ~/.xpdfrc or the sys-
+              tem-wide config file.
+
+       -v     Print copyright and version information.
+
+       -h     Print usage information.   (-help  and  --help  are
+              equivalent.)
+
+                                                               ()
+
+2 BUGS
+
+       Some  PDF  files  contain  fonts whose encodings have been
+       mangled beyond recognition.  There is  no  way  (short  of
+       OCR) to extract text from these files.
+
+                                                               ()
+
+2 XIT_CODE
+
+       The Xpdf tools use the following exit codes:
+
+       0      No error.
+
+       1      Error opening a PDF file.
+
+       2      Error opening an output file.
+
+       3      Error related to PDF permissions.
+
+       99     Other error.
+
+                                                               ()
+
+2 AUTHOR
+
+       The  pdftotext  software  and  documentation are copyright
+       1996-2005 Glyph & Cog, LLC.
+
+                                                               ()
+
+2 SEE_ALSO
+
+       xpdf(1), pdftops(1), pdfinfo(1), pdffonts(1), pdftoppm(1),
+       pdfimages(1), xpdfrc(5)
+       http://www.foolabs.com/xpdf/
+
+                                                               ()
+

data/pdf2json-0.52-source/doc/sample-xpdfrc

@@ -0,0 +1,91 @@
+#========================================================================
+#
+# Sample xpdfrc file
+#
+# The Xpdf tools look for a config file in two places:
+# 1. ~/.xpdfrc
+# 2. in a system-wide directory, typically /usr/local/etc/xpdfrc
+#
+# This sample config file demonstrates some of the more common
+# configuration options.  Everything here is commented out.  You
+# should edit things (especially the file/directory paths, since
+# they'll likely be different on your system), and uncomment whichever
+# options you want to use.  For complete details on config file syntax
+# and available options, please see the xpdfrc(5) man page.
+#
+# Also, the Xpdf language support packages each include a set of
+# options to be added to the xpdfrc file.
+#
+# http://www.foolabs.com/xpdf/
+#
+#========================================================================
+
+#----- display fonts
+
+# These map the Base-14 fonts to the Type 1 fonts that ship with
+# ghostscript.  You'll almost certainly want to use something like
+# this, but you'll need to adjust this to point to wherever
+# ghostscript is installed on your system.  (But if the fonts are
+# installed in a "standard" location, xpdf will find them
+# automatically.)
+
+#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
+
+# If you need to display PDF files that refer to non-embedded fonts,
+# you should add one or more fontDir options to point to the
+# directories containing the font files.  Xpdf will only look at .pfa,
+# .pfb, and .ttf files in those directories (other files will simply
+# be ignored).
+
+#fontDir		/usr/local/fonts/bakoma
+
+#----- PostScript output control
+
+# Set the default PostScript file or command.
+
+#psFile			"|lpr -Pmyprinter"
+
+# Set the default PostScript paper size -- this can be letter, legal,
+# A4, or A3.  You can also specify a paper size as width and height
+# (in points).
+
+#psPaperSize		letter
+
+#----- text output control
+
+# Choose a text encoding for copy-and-paste and for pdftotext output.
+# The Latin1, ASCII7, and UTF-8 encodings are built into Xpdf.  Other
+# encodings are available in the language support packages.
+
+#textEncoding		UTF-8
+
+# Choose the end-of-line convention for multi-line copy-and-past and
+# for pdftotext output.  The available options are unix, mac, and dos.
+
+#textEOL		unix
+
+#----- misc settings
+
+# Enable t1lib, FreeType, and anti-aliased text.
+
+#enableT1lib		yes
+#enableFreeType		yes
+#antialias		yes
+
+# Set the command used to run a web browser when a URL hyperlink is
+# clicked.
+
+#urlCommand	"netscape -remote 'openURL(%s)'"

data/pdf2json-0.52-source/doc/xpdf.1

@@ -0,0 +1,513 @@
+.\" Copyright 1996-2005 Glyph & Cog, LLC
+.TH xpdf 1 "17 August 2005"
+.SH NAME
+xpdf \- Portable Document Format (PDF) file viewer for X (version 3.01)
+.SH SYNOPSIS
+.B xpdf
+[options]
+.RI [ PDF-file
+.RI [ page " | +" dest ]]
+.SH DESCRIPTION
+.B Xpdf
+is a viewer for Portable Document Format (PDF) files.  (These are also
+sometimes also called \'Acrobat' files, from the name of Adobe's PDF
+software.)  Xpdf runs under the X Window System on UNIX, VMS, and
+OS/2.
+.PP
+To run xpdf, simply type:
+.PP
+.RS
+xpdf file.pdf
+.RE
+.PP
+where
+.I file.pdf
+is your PDF file.  The file name can be followed by a number
+specifying the page which should be displayed first, e.g.:
+.PP
+.RS
+xpdf file.pdf 18
+.RE
+.PP
+You can also give a named destination, prefixed with \'+' in place of
+the page number.  (This is only useful with PDF files that provide
+named destination targets.)
+.PP
+You can also start xpdf without opening any files:
+.PP
+.RS
+xpdf
+.RE
+.SH CONFIGURATION FILE
+Xpdf reads a configuration file at startup.  It first tries to find
+the user's private config file, ~/.xpdfrc.  If that doesn't exist, it
+looks for a system-wide config file, typically /usr/local/etc/xpdfrc
+(but this location can be changed when xpdf is built).  See the
+.BR xpdfrc (5)
+man page for details.
+.SH OPTIONS
+Many of the following options can be set with configuration file
+commands or X resources.  These are listed in square brackets with the
+description of the corresponding command line option.
+.TP
+.BI \-g " geometry"
+Set the initial window geometry.
+.RB ( \-geometry
+is equivalent.)
+.RB "[X resource: " xpdf.geometry ]
+.TP
+.BI \-title " title"
+Set the window title.  By default, the title will be "xpdf: foo.pdf".
+.RB "[X resource: " xpdf.title ]
+.TP
+.B \-cmap
+Install a private colormap.  This is ignored on TrueColor visuals.
+.RB "[X resource: " xpdf.installCmap ]
+.TP
+.BI \-rgb " number"
+Set the size of largest RGB cube xpdf will try to allocate.  The
+default is 5 (for a 5x5x5 cube); set to a smaller number to conserve
+color table entries.  This is ignored with private colormaps and on
+TrueColor visuals.
+.RB "[X resource: " xpdf.rgbCubeSize ]
+.TP
+.B \-rv
+Set reverse video mode.  This reverses the colors of everything except
+images.  It may not always produce great results for PDF files which
+do weird things with color.  This also causes the paper color to
+default to black.
+.RB "[X resource: " xpdf.reverseVideo ]
+.TP
+.BI \-papercolor " color"
+Set the "paper color", i.e., the background of the page display.  This
+will not work too well with PDF files that do things like filling in
+white behind the text.
+.RB "[X resource: " xpdf.paperColor ]
+.TP
+.BI \-mattecolor " color"
+Set the matte color, i.e., the color used for background outside the
+actual page area.
+.RB "[X resource: " xpdf.matteColor ]
+.TP
+.BI \-z " zoom"
+Set 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.
+.RB "[config file: " initialZoom "; or X resource: " xpdf.initialZoom ]
+.TP
+.B \-cont
+Start in continuous view mode, i.e., with one vertical scroll bar for
+the whole document.
+.RB "[config file: " continuousView ]
+.TP
+.BI \-t1lib " yes | no"
+Enable or disable t1lib (a Type 1 font rasterizer).  This defaults to
+"yes".
+.RB "[config file: " enableT1lib ]
+.TP
+.BI \-freetype " yes | no"
+Enable or disable FreeType (a TrueType / Type 1 font rasterizer).
+This defaults to "yes".
+.RB "[config file: " enableFreeType ]
+.TP
+.BI \-aa " yes | no"
+Enable or disable font anti-aliasing.  This defaults to "yes".
+.RB "[config file: " antialias ]
+.TP
+.BI \-ps " PS-file"
+Set the default file name for PostScript output (i.e., the name which
+will appear in the print dialog).  This can also be of the form
+\'|command' to pipe the PostScript through a command.
+.RB "[config file: " psFile ]
+.TP
+.BI \-paper " size"
+Set the paper size to one of "letter", "legal", "A4", or "A3".  This
+can also be set to "match", which will set the paper size to match the
+size specified in the PDF file.
+.RB "[config file: " psPaperSize ]
+.TP
+.BI \-paperw " size"
+Set the paper width, in points.
+.RB "[config file: " psPaperSize ]
+.TP
+.BI \-paperh " size"
+Set the paper height, in points.
+.RB "[config file: " psPaperSize ]
+.TP
+.B \-level1
+Generate Level 1 PostScript.  The resulting PostScript files will be
+significantly larger (if they contain images), but will print on Level
+1 printers.  This also converts all images to black and white.
+.RB "[config file: " psLevel ]
+.TP
+.BI \-enc " encoding-name"
+Sets the encoding to use for text output.  The
+.I encoding\-name
+must be defined with the unicodeMap command (see
+.BR xpdfrc (5)).
+This defaults to "Latin1" (which is a built-in encoding).
+.RB "[config file: " textEncoding ]
+.TP
+.BI \-eol " unix | dos | mac"
+Sets the end-of-line convention to use for text output.
+.RB "[config file: " textEOL ]
+.TP
+.BI \-opw " password"
+Specify the owner password for the PDF file.  Providing this will
+bypass all security restrictions.
+.TP
+.BI \-upw " password"
+Specify the user password for the PDF file.
+.TP
+.B \-fullscreen
+Open xpdf in a full-screen mode, useful for presentations.  You may
+also want to specify '-bg black' (or similar) with this.  (There is
+currently no way to switch between window and full-screen modes on the
+fly.)
+.TP
+.BI \-remote " name"
+Start/contact xpdf remote server with specified name (see the
+.B "REMOTE SERVER MODE"
+section below).
+.TP
+.B \-reload
+Reload xpdf remote server window (with -remote only).
+.TP
+.B \-raise
+Raise xpdf remote server window (with -remote only).
+.TP
+.B \-quit
+Kill xpdf remote server (with -remote only).
+.TP
+.B \-cmd
+Print commands as they're executed (useful for debugging).
+.RB "[config file: " printCommands ]
+.TP
+.B \-q
+Don't print any messages or errors.
+.RB "[config file: " errQuiet ]
+.TP
+.BI \-cfg " config-file"
+Read
+.I config-file
+in place of ~/.xpdfrc or the system-wide config file.
+.TP
+.B \-v
+Print copyright and version information.
+.TP
+.B \-h
+Print usage information.
+.RB ( \-help
+and
+.B \-\-help
+are equivalent.)
+.PP
+Several other standard X options and resources will work as expected:
+.TP
+.BI \-display " display"
+.RB "[X resource: " xpdf.display ]
+.TP
+.BI \-fg " color"
+.RB ( \-foreground
+is equivalent.)
+.RB "[X resource: " xpdf*Foreground ]
+.TP
+.BI \-bg " color"
+.RB ( \-background
+is equivalent.)
+.RB "[X resource: " xpdf*Background ]
+.TP
+.BI \-font " font"
+.RB ( \-fn
+is equivalent.)
+.RB "[X resource: " xpdf*fontList ]
+.PP
+The color and font options only affect the user interface elements,
+not the PDF display (the \'paper').
+.PP
+The following X resources do not have command line option equivalents:
+.TP
+.B xpdf.viKeys
+Enables the \'h', \'l', \'k' and \'j' keys for left, right, up, and
+down scrolling.
+.TP
+.B xpdf.toolTipEnable
+Enables (if set to true) or disables (if set to false) the tool-tips
+on the toolbar buttons.
+.SH CONTROLS
+.SS On-screen controls, at the bottom of the xpdf window
+.TP
+.B "left/right arrow buttons"
+Move to the previous/next page.
+.TP
+.B "double left/right arrow buttons"
+Move backward or forward by ten pages.
+.TP
+.B "dashed left/right arrow buttons"
+Move backward or forward along the history path.
+.TP
+.B "\'Page' entry box"
+Move to a specific page number.  Click in the box to activate it, type
+the page number, then hit return.
+.TP
+.B "zoom popup menu"
+Change the zoom factor (see the description of the -z option above).
+.TP
+.B "binoculars button"
+Find a text string.
+.TP
+.B "print button"
+Bring up a dialog for generating a PostScript file.  The dialog has
+options to set the pages to be printed and the PostScript file name.
+The file name can be \'-' for stdout or \'|command' to pipe the
+PostScript through a command, e.g., \'|lpr'.
+.TP
+.B "\'?' button"
+Bring up the \'about xpdf' window.
+.TP
+.B "link info"
+The space between the \'?' and \'Quit' buttons is used to show the URL
+or external file name when the mouse is over a link.
+.TP
+.B "\'Quit' button"
+Quit xpdf.
+.PP
+.SS Menu
+Pressing the right mouse button will post a popup menu with the
+following commands:
+.TP
+.B "Open..."
+Open a new PDF file via a file requester.
+.TP
+.B "Open in new window..."
+Create a new window and open a new PDF file via a file requester.
+.TP
+.B "Reload"
+Reload the current PDF file.  Note that Xpdf will reload the file
+automatically (on a page change or redraw) if it has changed since it
+was last loaded.
+.TP
+.B "Save as..."
+Save the current file via a file requester.
+.TP
+.B "Continuous view"
+Toggles between single page and continuous view modes.
+.TP
+.B "Rotate counterclockwise"
+Rotate the page 90 degrees counterclockwise.
+.TP
+.B "Rotate clockwise"
+Rotate the page 90 degrees clockwise.  The two rotate commands are
+intended primarily for PDF files where the rotation isn't correctly
+specified in the file.
+.TP
+.B "Close"
+Close the current window.  If this is the only open window, the
+document is closed, but the window is left open (i.e., this menu
+command won't quit xpdf).
+.TP
+.B "Quit"
+Quit xpdf.
+.PP
+.SS Outline
+If the PDF contains an outline (a.k.a., bookmarks), there will be an
+outline pane on the left side of the window.  The width of the outline
+pane is adjustable with a vertical split bar via the knob near its
+bottom end.
+.PP
+.SS Text selection
+Dragging the mouse with the left button held down will highlight an
+arbitrary rectangle.  Any text inside this rectangle will be copied to
+the X selection buffer.
+.PP
+.SS Links
+Clicking on a hyperlink will jump to the link's destination.  A link
+to another PDF document will make xpdf load that document.  A
+\'launch' link to an executable program will display a dialog, and if
+you click \'ok', execute the program.  URL links call an external
+command (see the
+.B WEB BROWSERS
+section below).
+.PP
+.SS Panning
+Dragging the mouse with the middle button held down pans the window.
+.PP
+.SS Key bindings
+.TP
+.B o
+Open a new PDF file via a file requester.
+.TP
+.B r
+Reload the current PDF file.  Note that Xpdf will reload the file
+automatically (on a page change or redraw) if it has changed since it
+was last loaded.
+.TP
+.B control-L
+Redraw the current page.
+.TP
+.B control-W
+Close the current window.
+.TP
+.B f or control-F
+Find a text string.
+.TP
+.B control-G
+Find next occurrence.
+.TP
+.B control-P
+Print.
+.TP
+.B n
+Move to the next page.  Scrolls to the top of the page, unless scroll
+lock is turned on.
+.TP
+.B p
+Move to the previous page.  Scrolls to the top of the page, unless
+scroll lock is turned on.
+.TP
+.BR <Space> " or " <PageDown> " or " <Next>
+Scroll down on the current page; if already at bottom, move to next
+page.
+.TP
+.BR <Backspace> " or " <Delete> " or " <PageUp> " or " <Previous>
+Scroll up on the current page; if already at top, move to previous
+page.
+.TP
+.B v
+Move forward along the history path.
+.TP
+.B b
+Move backward along the history path.
+.TP
+.B <Home>
+Scroll to top of current page.
+.TP
+.B <End>
+Scroll to bottom of current page.
+.TP
+.B control-<Home>
+Scroll to first page of document.
+.TP
+.B control-<End>
+Scroll to last page of document.
+.TP
+.B arrows
+Scroll the current page.
+.TP
+.B g
+Activate the page number text field ("goto page").
+.TP
+.B 0
+Set the zoom factor to 125%.
+.TP
+.B +
+Zoom in (increment the zoom factor by 1).
+.TP
+.B -
+Zoom out (decrement the zoom factor by 1).
+.TP
+.B z
+Set the zoom factor to 'page' (fit page to window).
+.TP
+.B w
+Set the zoom factor to 'width' (fit page width to window).
+.TP
+.B q
+Quit xpdf.
+.SH "WEB BROWSERS"
+If you want to run xpdf automatically from netscape or mosaic (and
+probably other browsers) when you click on a link to a PDF file, you
+need to edit (or create) the files
+.I .mime.types
+and
+.I .mailcap
+in your home directory.  In
+.I .mime.types
+add the line:
+.PP
+.RS
+application/pdf pdf
+.RE
+.PP
+In
+.I .mailcap
+add the lines:
+.PP
+.RS
+# Use xpdf to view PDF files.
+.RE
+.RS
+application/pdf; xpdf -q %s
+.RE
+.PP
+Make sure that xpdf is on your executable search path.
+.PP
+When you click on a URL link in a PDF file, xpdf will execute the
+command specified by the urlCommand config file option, replacing an
+occurrence of \'%s' with the URL.  For example, to call netscape with
+the URL, add this line to your config file:
+.PP
+.RS
+urlCommand "netscape -remote 'openURL(%s)'"
+.RE
+.SH "REMOTE SERVER MODE"
+Xpdf can be started in remote server mode by specifying a server name
+(in addition to the file name and page number).  For example:
+.PP
+.RS
+xpdf -remote myServer file.pdf
+.RE
+.PP
+If there is currently no xpdf running in server mode with the name
+\'myServer', a new xpdf window will be opened.  If another command:
+.PP
+.RS
+xpdf -remote myServer another.pdf 9
+.RE
+.PP
+is issued, a new copy of xpdf will not be started.  Instead, the first
+xpdf (the server) will load
+.I another.pdf
+and display page nine.  If the file name is the same:
+.PP
+.RS
+xpdf -remote myServer another.pdf 4
+.RE
+.PP
+the xpdf server will simply display the specified page.
+.PP
+The -raise option tells the server to raise its window; it can be
+specified with or without a file name and page number.
+.PP
+The -quit option tells the server to close its window and exit.
+.SH EXIT CODES
+The Xpdf tools use the following exit codes:
+.TP
+0
+No error.
+.TP
+1
+Error opening a PDF file.
+.TP
+2
+Error opening an output file.
+.TP
+3
+Error related to PDF permissions.
+.TP
+99
+Other error.
+.SH AUTHOR
+The xpdf software and documentation are copyright 1996-2005 Glyph &
+Cog, LLC.
+.SH "SEE ALSO"
+.BR pdftops (1),
+.BR pdftotext (1),
+.BR pdfinfo (1),
+.BR pdffonts (1),
+.BR pdftoppm (1),
+.BR pdfimages (1),
+.BR xpdfrc (5)
+.br
+.B http://www.foolabs.com/xpdf/