dany/pdfio
1
0
Fork 0
mirror of https://github.com/michaelrsweet/pdfio.git synced 2024-12-25 21:08:21 +01:00
Code Issues Packages Projects Releases Wiki Activity

Move pdfiototext to examples.

Browse Source
This commit is contained in:
Michael R Sweet 2024-12-22 19:00:17 -05:00
parent aa91b141a8
commit ed1421287f
No known key found for this signature in database
GPG Key ID: BE67C75EC81F3244
4 changed files with 13 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@ -14,6 +14,7 @@
/examples/code128 /examples/code128
/examples/image2pdf /examples/image2pdf
/examples/md2pdf /examples/md2pdf
/examples/pdf2text
/examples/pdfioinfo /examples/pdfioinfo
/Makefile /Makefile
/packages /packages
@ -21,7 +22,6 @@
/pdfio.xcodeproj/xcshareddata /pdfio.xcodeproj/xcshareddata
/pdfio-*.tar.gz* /pdfio-*.tar.gz*
/pdfio-*.zip* /pdfio-*.zip*
/pdfiototext
/testpdfio /testpdfio
/testpdfio-*.pdf /testpdfio-*.pdf
/testttf /testttf

8
Makefile.in
View File

@ -103,13 +103,11 @@ LIBOBJS = \
ttf.o ttf.o
OBJS = \ OBJS = \
$(LIBOBJS) \ $(LIBOBJS) \
pdfiototext.o \
testpdfio.o \ testpdfio.o \
testttf.o testttf.o
TARGETS = \ TARGETS = \
$(LIBPDFIO) \ $(LIBPDFIO) \
$(LIBPDFIO_STATIC) \ $(LIBPDFIO_STATIC) \
pdfiototext \
testpdfio \ testpdfio \
testttf testttf
@ -201,12 +199,6 @@ pdfio1.def: $(LIBOBJS) Makefile
grep -v '^_ttf' | sed -e '1,$$s/^_//' | sort >>$@ grep -v '^_ttf' | sed -e '1,$$s/^_//' | sort >>$@
# pdfio text extraction (demo, doesn't handle a lot of things yet)
pdfiototext: pdfiototext.o libpdfio.a
echo Linking $@...
$(CC) $(LDFLAGS) -o $@ pdfiototext.o libpdfio.a $(LIBS)
# pdfio test program # pdfio test program
testpdfio: testpdfio.o libpdfio.a testpdfio: testpdfio.o libpdfio.a
echo Linking $@... echo Linking $@...

6
examples/Makefile
View File

@ -23,6 +23,7 @@ TARGETS = \
code128 \ code128 \
image2pdf \ image2pdf \
md2pdf \ md2pdf \
pdf2text \
pdfioinfo pdfioinfo
@ -50,6 +51,11 @@ md2pdf: md2pdf.c mmd.c mmd.h
$(CC) $(CFLAGS) -o $@ md2pdf.c mmd.c $(LIBS) $(CC) $(CFLAGS) -o $@ md2pdf.c mmd.c $(LIBS)
# pdfio text extraction (demo, doesn't handle a lot of things yet)
pdf2text: pdf2text.c
$(CC) $(CFLAGS) -o $@ pdf2text.c $(LIBS)
# pdfioinfo # pdfioinfo
pdfioinfo: pdfioinfo.c pdfioinfo: pdfioinfo.c
$(CC) $(CFLAGS) -o $@ pdfioinfo.c $(LIBS) $(CC) $(CFLAGS) -o $@ pdfioinfo.c $(LIBS)

18
pdfiototext.c → examples/pdf2text.c
View File

@ -1,17 +1,17 @@
// //
// PDF to text program for PDFio. // PDF to text program for PDFio.
// //
// Copyright © 2022 by Michael R Sweet. // Copyright © 2022-2024 by Michael R Sweet.
// //
// Licensed under Apache License v2.0. See the file "LICENSE" for more // Licensed under Apache License v2.0. See the file "LICENSE" for more
// information. // information.
// //
// Usage: // Usage:
// //
// ./pdfiototext FILENAME.pdf > FILENAME.txt // ./pdf2text FILENAME.pdf > FILENAME.txt
// //
#include "pdfio.h" #include <pdfio.h>
#include <string.h> #include <string.h>
@ -36,16 +36,14 @@ main(int argc, // I - Number of command-line arguments
// Verify command-line arguments... // Verify command-line arguments...
if (argc != 2) if (argc != 2)
{ {
puts("Usage: pdfiototext FILENAME.pdf > FILENAME.txt"); puts("Usage: pdf2text FILENAME.pdf > FILENAME.txt");
return (1); return (1);
} }
// Open the PDF file... // Open the PDF file...
if ((file = pdfioFileOpen(argv[1], NULL, NULL, NULL, NULL)) == NULL) if ((file = pdfioFileOpen(argv[1], /*password_cb*/NULL, /*password_data*/NULL, /*error_cb*/NULL, /*error_data*/NULL)) == NULL)
return (1); return (1);
// printf("%s: %u pages\n", argv[1], (unsigned)pdfioFileGetNumPages(file));
// Try grabbing content from all of the pages... // Try grabbing content from all of the pages...
for (i = 0, num_pages = pdfioFileGetNumPages(file); i < num_pages; i ++) for (i = 0, num_pages = pdfioFileGetNumPages(file); i < num_pages; i ++)
{ {
@ -54,15 +52,11 @@ main(int argc, // I - Number of command-line arguments
num_streams = pdfioPageGetNumStreams(obj); 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 ++) for (j = 0; j < num_streams; j ++)
{ {
if ((st = pdfioPageOpenStream(obj, j, true)) == NULL) if ((st = pdfioPageOpenStream(obj, j, true)) == NULL)
continue; continue;
// printf("%s: page%u st%u=%p\n", argv[1], (unsigned)i, (unsigned)j, st);
first = true; first = true;
while (pdfioStreamGetToken(st, buffer, sizeof(buffer))) while (pdfioStreamGetToken(st, buffer, sizeof(buffer)))
{ {
@ -70,7 +64,7 @@ main(int argc, // I - Number of command-line arguments
{ {
if (first) if (first)
first = false; first = false;
else else if (buffer[1] != ' ')
putchar(' '); putchar(' ');
fputs(buffer + 1, stdout); fputs(buffer + 1, stdout);