Add missing pdfioPageGetNumStreams and pdfioPageOpenStream functions.

Add initial version of pdfiototext text extraction utility.

.gitignore

@@ -8,6 +8,7 @@
 /doc/pdfio.epub
 /packages
 /pdfio.xcodeproj/xcshareddata
+/pdfiototext
 /testpdfio
 /testpdfio-*.pdf
 /x64

CHANGES.md

@@ -2,6 +2,13 @@ Changes in PDFio
 ================
 
 
+v1.0.1 (Month DD, YYYY)
+-----------------------
+
+- Added missing `pdfioPageGetNumStreams` and `pdfioPageOpenStream` functions.
+- Added pdfiototext demo utility.
+
+
 v1.0.0 (December 14, 2021)
 --------------------------
 

Makefile

@@ -1,7 +1,7 @@
 #
 # Makefile for PDFio.
 #
-# Copyright © 2021 by Michael R Sweet.
+# Copyright © 2021-2022 by Michael R Sweet.
 #
 # Licensed under Apache License v2.0.  See the file "LICENSE" for more
 # information.
@@ -26,7 +26,7 @@ DSONAME		=
 LDFLAGS		=
 LIBS		=	-lm -lz
 RANLIB		=	ranlib
-VERSION		=	1.0.0
+VERSION		=	1.0.1
 prefix		=	/usr/local
 
 
@@ -62,10 +62,12 @@ LIBOBJS		=	\
 			ttf.o
 OBJS		=	\
 			$(LIBOBJS) \
+			pdfiototext.o \
 			testpdfio.o
 TARGETS		=	\
 			$(DSONAME) \
 			libpdfio.a \
+			pdfiototext \
 			testpdfio
 
 
@@ -154,6 +156,11 @@ pdfio1.def: $(LIBOBJS) Makefile
 		grep -v '^_ttf' | sed -e '1,$$s/^_//' | sort >>$@
 
 
+# pdfio text extraction demo
+pdfiototext:		pdfiototext.o libpdfio.a
+	$(CC) $(LDFLAGS) $(COMMONFLAGS) -o $@ pdfiototext.o libpdfio.a $(LIBS)
+
+
 # pdfio test program
 testpdfio:		testpdfio.o libpdfio.a
 	$(CC) $(LDFLAGS) $(COMMONFLAGS) -o $@ testpdfio.o libpdfio.a $(LIBS)
@@ -167,7 +174,7 @@ ttf.o:			ttf.h
 # Make documentation using Codedoc <https://www.msweet.org/codedoc>
 DOCFLAGS	=	\
 			--author "Michael R Sweet" \
-			--copyright "Copyright (c) 2021 by Michael R Sweet" \
+			--copyright "Copyright (c) 2021-2022 by Michael R Sweet" \
 			--docversion $(VERSION)
 
 .PHONY: doc

pdfio-page.c

@@ -1,7 +1,7 @@
 //
 // PDF page functions for PDFio.
 //
-// Copyright © 2021 by Michael R Sweet.
+// Copyright © 2021-2022 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@@ -14,6 +14,13 @@
 #include "pdfio-private.h"
 
 
+//
+// Local functions...
+//
+
+static _pdfio_value_t	*get_contents(pdfio_obj_t *page);
+
+
 //
 // 'pdfioPageCopy()' - Copy a page to a PDF file.
 //
@@ -47,3 +54,74 @@ pdfioPageCopy(pdfio_file_t *pdf,	// I - PDF file
   else
     return (_pdfioFileAddPage(pdf, dstpage));
 }
+
+
+//
+// 'pdfioPageGetNumStreams()' - Get the number of content streams for a page object.
+//
+
+size_t					// O - Number of streams
+pdfioPageGetNumStreams(
+    pdfio_obj_t *page)			// I - Page object
+{
+  _pdfio_value_t *contents = get_contents(page);
+					// Contents value
+
+
+  if (!contents)
+    return (0);
+  else if (contents->type == PDFIO_VALTYPE_ARRAY)
+    return (pdfioArrayGetSize(contents->value.array));
+  else
+    return (1);
+}
+
+
+//
+// 'pdfioPageOpenStream()' - Open a content stream for a page.
+//
+
+pdfio_stream_t *			// O - Stream
+pdfioPageOpenStream(
+    pdfio_obj_t *page,			// I - Page object
+    size_t      n,			// I - Stream index (0-based)
+    bool        decode)			// I - `true` to decode/decompress stream
+{
+  _pdfio_value_t *contents = get_contents(page);
+					// Contents value
+
+
+  if (!contents)
+    return (NULL);
+  else if (contents->type == PDFIO_VALTYPE_ARRAY && n < pdfioArrayGetSize(contents->value.array))
+    return (pdfioObjOpenStream(pdfioArrayGetObj(contents->value.array, n), decode));
+  else if (n)
+    return (NULL);
+  else
+    return (pdfioObjOpenStream(pdfioFileFindObj(page->pdf, contents->value.indirect.number), decode));
+}
+
+
+//
+// 'get_contents()' - Get a page's Contents value.
+//
+
+static _pdfio_value_t *			// O - Value or NULL on error
+get_contents(pdfio_obj_t *page)		// I - Page object
+{
+  // Range check input...
+  if (!page)
+    return (NULL);
+
+  // Load the page object as needed...
+  if (page->value.type == PDFIO_VALTYPE_NONE)
+  {
+    if (!_pdfioObjLoad(page))
+      return (NULL);
+  }
+
+  if (page->value.type != PDFIO_VALTYPE_DICT)
+    return (NULL);
+
+  return (_pdfioDictGetValue(page->value.value.dict, "Contents"));
+}

pdfiototext.c

@@ -0,0 +1,90 @@
+//
+// PDF to text program for PDFio.
+//
+// Copyright © 2022 by Michael R Sweet.
+//
+// Licensed under Apache License v2.0.  See the file "LICENSE" for more
+// information.
+//
+// Usage:
+//
+//   ./pdfiototext FILENAME.pdf > FILENAME.txt
+//
+
+#include "pdfio.h"
+
+
+//
+// 'main()' - Main entry.
+//
+
+int					// O - Exit status
+main(int  argc,				// I - Number of command-line arguments
+     char *argv[])			// I - Command-line arguments
+{
+  pdfio_file_t	*file;			// PDF file
+  size_t	i, j,			// Looping vars
+		num_pages,		// Number of pages
+		num_streams;		// Number of streams for page
+  pdfio_obj_t	*obj;			// Current page object
+  pdfio_stream_t *st;			// Current page content stream
+  char		buffer[1024];		// String buffer
+  bool		first;			// First string token?
+
+
+  // Verify command-line arguments...
+  if (argc != 2)
+  {
+    puts("Usage: pdfiototext FILENAME.pdf > FILENAME.txt");
+    return (1);
+  }
+
+  // Open the PDF file...
+  if ((file = pdfioFileOpen(argv[1], NULL, NULL, NULL, NULL)) == NULL)
+    return (1);
+
+  printf("%s: %u pages\n", argv[1], (unsigned)pdfioFileGetNumPages(file));
+
+  // Try grabbing content from all of the pages...
+  for (i = 0, num_pages = pdfioFileGetNumPages(file); i < num_pages; i ++)
+  {
+    if ((obj = pdfioFileGetPage(file, i)) == NULL)
+      continue;
+
+    num_streams = pdfioPageGetNumStreams(obj);
+
+    printf("%s: page%u=%p, num_streams=%u\n", argv[1], (unsigned)i, obj, (unsigned)num_streams);
+
+    for (j = 0; j < num_streams; j ++)
+    {
+      if ((st = pdfioPageOpenStream(obj, j, true)) == NULL)
+	continue;
+
+      printf("%s: page%u st%u=%p\n", argv[1], (unsigned)i, (unsigned)j, st);
+
+      first = true;
+      while (pdfioStreamGetToken(st, buffer, sizeof(buffer)))
+      {
+	if (buffer[0] == '(')
+	{
+	  if (first)
+	  {
+	    putchar(' ');
+	    first = false;
+	  }
+
+	  fputs(buffer + 1, stdout);
+	}
+      }
+
+      if (!first)
+	putchar('\n');
+
+      pdfioStreamClose(st);
+    }
+  }
+
+  pdfioFileClose(file);
+
+  return (0);
+}