![]() |
Leptonica
1.83.1
Image processing and image analysis suite
|
#include <string.h>
#include <math.h>
#include "allheaders.h"
Go to the source code of this file.
Functions | |
l_ok | convertFilesToPdf (const char *dirname, const char *substr, l_int32 res, l_float32 scalefactor, l_int32 type, l_int32 quality, const char *title, const char *fileout) |
l_ok | saConvertFilesToPdf (SARRAY *sa, l_int32 res, l_float32 scalefactor, l_int32 type, l_int32 quality, const char *title, const char *fileout) |
l_ok | saConvertFilesToPdfData (SARRAY *sa, l_int32 res, l_float32 scalefactor, l_int32 type, l_int32 quality, const char *title, l_uint8 **pdata, size_t *pnbytes) |
l_ok | selectDefaultPdfEncoding (PIX *pix, l_int32 *ptype) |
l_ok | convertUnscaledFilesToPdf (const char *dirname, const char *substr, const char *title, const char *fileout) |
l_ok | saConvertUnscaledFilesToPdf (SARRAY *sa, const char *title, const char *fileout) |
l_ok | saConvertUnscaledFilesToPdfData (SARRAY *sa, const char *title, l_uint8 **pdata, size_t *pnbytes) |
l_ok | convertUnscaledToPdfData (const char *fname, const char *title, l_uint8 **pdata, size_t *pnbytes) |
l_ok | pixaConvertToPdf (PIXA *pixa, l_int32 res, l_float32 scalefactor, l_int32 type, l_int32 quality, const char *title, const char *fileout) |
l_ok | pixaConvertToPdfData (PIXA *pixa, l_int32 res, l_float32 scalefactor, l_int32 type, l_int32 quality, const char *title, l_uint8 **pdata, size_t *pnbytes) |
l_ok | convertToPdf (const char *filein, l_int32 type, l_int32 quality, const char *fileout, l_int32 x, l_int32 y, l_int32 res, const char *title, L_PDF_DATA **plpd, l_int32 position) |
l_ok | convertImageDataToPdf (l_uint8 *imdata, size_t size, l_int32 type, l_int32 quality, const char *fileout, l_int32 x, l_int32 y, l_int32 res, const char *title, L_PDF_DATA **plpd, l_int32 position) |
l_ok | convertToPdfData (const char *filein, l_int32 type, l_int32 quality, l_uint8 **pdata, size_t *pnbytes, l_int32 x, l_int32 y, l_int32 res, const char *title, L_PDF_DATA **plpd, l_int32 position) |
l_ok | convertImageDataToPdfData (l_uint8 *imdata, size_t size, l_int32 type, l_int32 quality, l_uint8 **pdata, size_t *pnbytes, l_int32 x, l_int32 y, l_int32 res, const char *title, L_PDF_DATA **plpd, l_int32 position) |
l_ok | pixConvertToPdf (PIX *pix, l_int32 type, l_int32 quality, const char *fileout, l_int32 x, l_int32 y, l_int32 res, const char *title, L_PDF_DATA **plpd, l_int32 position) |
l_ok | pixWriteStreamPdf (FILE *fp, PIX *pix, l_int32 res, const char *title) |
l_ok | pixWriteMemPdf (l_uint8 **pdata, size_t *pnbytes, PIX *pix, l_int32 res, const char *title) |
l_ok | convertSegmentedFilesToPdf (const char *dirname, const char *substr, l_int32 res, l_int32 type, l_int32 thresh, BOXAA *baa, l_int32 quality, l_float32 scalefactor, const char *title, const char *fileout) |
BOXAA * | convertNumberedMasksToBoxaa (const char *dirname, const char *substr, l_int32 numpre, l_int32 numpost) |
l_ok | convertToPdfSegmented (const char *filein, l_int32 res, l_int32 type, l_int32 thresh, BOXA *boxa, l_int32 quality, l_float32 scalefactor, const char *title, const char *fileout) |
l_ok | pixConvertToPdfSegmented (PIX *pixs, l_int32 res, l_int32 type, l_int32 thresh, BOXA *boxa, l_int32 quality, l_float32 scalefactor, const char *title, const char *fileout) |
l_ok | convertToPdfDataSegmented (const char *filein, l_int32 res, l_int32 type, l_int32 thresh, BOXA *boxa, l_int32 quality, l_float32 scalefactor, const char *title, l_uint8 **pdata, size_t *pnbytes) |
l_ok | pixConvertToPdfDataSegmented (PIX *pixs, l_int32 res, l_int32 type, l_int32 thresh, BOXA *boxa, l_int32 quality, l_float32 scalefactor, const char *title, l_uint8 **pdata, size_t *pnbytes) |
l_ok | concatenatePdf (const char *dirname, const char *substr, const char *fileout) |
l_ok | saConcatenatePdf (SARRAY *sa, const char *fileout) |
l_ok | ptraConcatenatePdf (L_PTRA *pa, const char *fileout) |
l_ok | concatenatePdfToData (const char *dirname, const char *substr, l_uint8 **pdata, size_t *pnbytes) |
l_ok | saConcatenatePdfToData (SARRAY *sa, l_uint8 **pdata, size_t *pnbytes) |
Variables | |
static const l_int32 | DefaultInputRes = 300 |
Higher-level operations for generating pdf from images. Use poppler's pdftoppm or pdfimages to invert the process, extracting raster images from pdf. |=============================================================| | Important notes | |=============================================================| | Some of these functions require I/O libraries such as | | libtiff, libjpeg, libpng, libz and libopenjp2. If you do | | not have these libraries, some calls will fail. For | | example, if you do not have libopenjp2, you cannot write a | | pdf where transcoding is required to incorporate a | | jp2k image. | | | | You can manually deactivate all pdf writing by setting | | this in environ.h: | || | This will link the stub file pdfiostub.c. | |=============================================================| Set 1. These functions convert a set of image files to a multi-page pdf file, with one image on each page. All images are rendered at the same (input) resolution. The images can be specified as being in a directory, or they can be in an sarray. The output pdf can be either a file or an array of bytes in memory. Set 2. These functions are a special case of set 1, where no scaling or change in quality is required. For jpeg, jp2k and tiffg4 images, the bytes in each file can be directly incorporated into the output pdf, and the wrapping up of multiple image files is very fast. For non-interlaced png, the data bytes including the predictors can also be written directly into the flate pdf data. For other image formats transcoding is required, where the image data is first decompressed and then flate (gzip), DCT (jpeg) or tiffg4 (1 bpp) encodings are generated. Set 3. These functions convert a set of images in memory to a multi-page pdf, with one image on each page. The pdf output can be either a file or an array of bytes in memory. Set 4. These functions implement a pdf output "device driver" for wrapping (encoding) any number of images on a single page in pdf. The input can be either an image file or a Pix; the pdf output can be either a file or an array of bytes in memory. Set 5. These "segmented" functions take a set of image files, along with optional segmentation information, and generate a multi-page pdf file, where each page consists in general of a mixed raster pdf of image and non-image regions. The segmentation information for each page can be input as either a mask over the image parts, or as a Boxa of those regions. Set 6. These "segmented" functions convert an image and an optional Boxa of image regions into a mixed raster pdf file for the page. The input image can be either a file or a Pix. Set 7. These functions take a set of single-page pdf files and concatenates it into a multi-page pdf. The input can be a set of either single page pdf files or pdf 'strings' in memory. The output can be either a file or an array of bytes in memory. The images in the pdf file can be rendered using a pdf viewer, such as evince, gv, xpdf or acroread. Reference on the pdf file format: http://www.adobe.com/devnet/pdf/pdf_reference_archive.html 1. Convert specified image files to pdf (one image file per page) l_int32 convertFilesToPdf() l_int32 saConvertFilesToPdf() l_int32 saConvertFilesToPdfData() l_int32 selectDefaultPdfEncoding() 2. Convert specified image files to pdf without scaling l_int32 convertUnscaledFilesToPdf() l_int32 saConvertUnscaledFilesToPdf() l_int32 saConvertUnscaledFilesToPdfData() l_int32 convertUnscaledToPdfData() 3. Convert multiple images to pdf (one image per page) l_int32 pixaConvertToPdf() l_int32 pixaConvertToPdfData() 4. Single page, multi-image converters l_int32 convertToPdf() l_int32 convertImageDataToPdf() l_int32 convertToPdfData() l_int32 convertImageDataToPdfData() l_int32 pixConvertToPdf() l_int32 pixWriteStreamPdf() l_int32 pixWriteMemPdf() 5. Segmented multi-page, multi-image converter l_int32 convertSegmentedFilesToPdf() BOXAA *convertNumberedMasksToBoxaa() 6. Segmented single page, multi-image converters l_int32 convertToPdfSegmented() l_int32 pixConvertToPdfSegmented() l_int32 convertToPdfDataSegmented() l_int32 pixConvertToPdfDataSegmented() 7. Multipage concatenation l_int32 concatenatePdf() l_int32 saConcatenatePdf() l_int32 ptraConcatenatePdf() l_int32 concatenatePdfToData() l_int32 saConcatenatePdfToData() The top-level multi-image functions can be visualized as follows: Output pdf data to file: convertToPdf() and convertImageDataToPdf() --> pixConvertToPdf() --> pixConvertToPdfData() Output pdf data to array in memory: convertToPdfData() and convertImageDataToPdfData() --> pixConvertToPdfData() The top-level segmented image functions can be visualized as follows: Output pdf data to file: convertToPdfSegmented() --> pixConvertToPdfSegmented() --> pixConvertToPdfDataSegmented() Output pdf data to array in memory: convertToPdfDataSegmented() --> pixConvertToPdfDataSegmented() For multi-page concatenation, there are three different types of input (1) directory and optional filename filter (2) sarray of filenames (3) ptra of byte arrays of pdf data and two types of output for the concatenated pdf data (1) filename (2) data array and size High-level interfaces are given for each of the six combinations. Note: When wrapping small images into pdf, it is useful to give them a relatively low resolution value, to avoid rounding errors when rendering the images. For example, if you want an image of width w pixels to be 5 inches wide on a screen, choose a resolution w/5. The very fast functions in section (2) require neither transcoding nor parsing of the compressed jpeg file. With three types of image compression, the compressed strings can be incorporated into the pdf data without decompression and re-encoding: jpeg, jp2k and png. The DCTDecode and JPXDecode filters can handle the entire jpeg and jp2k encoded string as a byte array in the pdf file. The FlateDecode filter can handle the png compressed image data, including predictors that occur as the first byte in each raster line, but it is necessary to store only the png IDAT chunk data in the pdf array. The alternative for wrapping png images is to transcode them: uncompress into a raster (a pix) and then gzip the raster data. This typically results in a larger pdf file because it doesn't use the two-dimensional png predictor. Colormaps, which are found in png PLTE chunks, must always be pulled out and included separately in the pdf. For CCITT-G4 compression, you can not simply include a tiff G4 file -- you must either parse it and extract the G4 compressed data within it, or uncompress to a raster and G4 compress again.|| #define USE_PDFIO 0 ||
Definition in file pdfio1.c.
l_ok concatenatePdf | ( | const char * | dirname, |
const char * | substr, | ||
const char * | fileout | ||
) |
[in] | dirname | directory name containing single-page pdf files |
[in] | substr | [optional] substring filter on filenames; can be null |
[in] | fileout | concatenated pdf file |
Notes: (1) This only works with leptonica-formatted single-page pdf files. (2) If substr is not NULL, only filenames that contain the substring can be returned. If substr == NULL, none of the filenames are filtered out. (3) The files in the directory, after optional filtering by the substring, are lexically sorted in increasing order before concatenation.
Definition at line 1993 of file pdfio1.c.
References getSortedPathnamesInDirectory(), saConcatenatePdf(), and sarrayDestroy().
l_ok concatenatePdfToData | ( | const char * | dirname, |
const char * | substr, | ||
l_uint8 ** | pdata, | ||
size_t * | pnbytes | ||
) |
[in] | dirname | directory name containing single-page pdf files |
[in] | substr | [optional] substring filter on filenames; can be null |
[out] | pdata | concatenated pdf data in memory |
[out] | pnbytes | number of bytes in pdf data |
Notes: (1) This only works with leptonica-formatted single-page pdf files. (2) If substr is not NULL, only filenames that contain the substring can be returned. If substr == NULL, none of the filenames are filtered out. (3) The files in the directory, after optional filtering by the substring, are lexically sorted in increasing order before concatenation.
Definition at line 2103 of file pdfio1.c.
References getSortedPathnamesInDirectory(), saConcatenatePdfToData(), and sarrayDestroy().
l_ok convertFilesToPdf | ( | const char * | dirname, |
const char * | substr, | ||
l_int32 | res, | ||
l_float32 | scalefactor, | ||
l_int32 | type, | ||
l_int32 | quality, | ||
const char * | title, | ||
const char * | fileout | ||
) |
[in] | dirname | directory name containing images |
[in] | substr | [optional] substring filter on filenames; can be null |
[in] | res | input resolution of all images |
[in] | scalefactor | scaling factor applied to each image; > 0.0 |
[in] | type | encoding type (L_JPEG_ENCODE, L_G4_ENCODE, L_FLATE_ENCODE, L_JP2K_ENCODE or L_DEFAULT_ENCODE for default) |
[in] | quality | for jpeg: 1-100; 0 for default (75) for jp2k: 27-45; 0 for default (34) |
[in] | title | [optional] pdf title; can be null |
[in] | fileout | pdf file of all images |
Notes: (1) If substr is not NULL, only image filenames that contain the substring can be used. If substr == NULL, all files in the directory are used. (2) The files in the directory, after optional filtering by the substring, are lexically sorted in increasing order before concatenation. (3) The scalefactor is applied to each image before encoding. If you enter a value <= 0.0, it will be set to 1.0. (4) Specifying one of the four encoding types for type forces all images to be compressed with that type. Use 0 to have the type determined for each image based on depth and whether or not it has a colormap.
Definition at line 252 of file pdfio1.c.
References getSortedPathnamesInDirectory(), saConvertFilesToPdf(), and sarrayDestroy().
Referenced by pixCompareWithTranslation().
l_ok convertImageDataToPdf | ( | l_uint8 * | imdata, |
size_t | size, | ||
l_int32 | type, | ||
l_int32 | quality, | ||
const char * | fileout, | ||
l_int32 | x, | ||
l_int32 | y, | ||
l_int32 | res, | ||
const char * | title, | ||
L_PDF_DATA ** | plpd, | ||
l_int32 | position | ||
) |
[in] | imdata | array of formatted image data; e.g., png, jpeg |
[in] | size | size of image data |
[in] | type | encoding type (L_JPEG_ENCODE, L_G4_ENCODE, L_FLATE_ENCODE, or L_JP2K_ENCODE) |
[in] | quality | for jpeg: 1-100; 0 for default (75) for jp2k: 27-45; 0 for default (34) |
[in] | fileout | output pdf file; only required on last image on page |
[in] | x,y | location of lower-left corner of image, in pixels, relative to the PostScript origin (0,0) at the lower-left corner of the page |
[in] | res | override the resolution of the input image, in ppi; use 0 to respect the resolution embedded in the input images |
[in] | title | [optional] pdf title; can be null |
[in,out] | plpd | ptr to lpd, which is created on the first invocation and returned until last image is processed, at which time it is destroyed |
[in] | position | in image sequence: L_FIRST_IMAGE, L_NEXT_IMAGE, L_LAST_IMAGE |
Notes: (1) If res == 0 and the input resolution field is 0, this will use DefaultInputRes. (2) See comments in convertToPdf().
Definition at line 1039 of file pdfio1.c.
References L_FLATE_ENCODE, L_G4_ENCODE, L_JP2K_ENCODE, L_JPEG_ENCODE, L_LAST_IMAGE, pixConvertToPdf(), pixDestroy(), pixReadMem(), and selectDefaultPdfEncoding().
l_ok convertImageDataToPdfData | ( | l_uint8 * | imdata, |
size_t | size, | ||
l_int32 | type, | ||
l_int32 | quality, | ||
l_uint8 ** | pdata, | ||
size_t * | pnbytes, | ||
l_int32 | x, | ||
l_int32 | y, | ||
l_int32 | res, | ||
const char * | title, | ||
L_PDF_DATA ** | plpd, | ||
l_int32 | position | ||
) |
[in] | imdata | array of formatted image data; e.g., png, jpeg |
[in] | size | size of image data |
[in] | type | encoding type (L_JPEG_ENCODE, L_G4_ENCODE, L_FLATE_ENCODE, or L_JP2K_ENCODE) |
[in] | quality | for jpeg: 1-100; 0 for default (75) for jp2k: 27-45; 0 for default (34) |
[out] | pdata | pdf data in memory |
[out] | pnbytes | number of bytes in pdf data |
[in] | x,y | location of lower-left corner of image, in pixels, relative to the PostScript origin (0,0) at the lower-left corner of the page |
[in] | res | override the resolution of the input image, in ppi; use 0 to respect the resolution embedded in the input images |
[in] | title | [optional] pdf title; can be null |
[out] | plpd | ptr to lpd, which is created on the first invocation and returned until last image is processed, at which time it is destroyed |
[in] | position | in image sequence: L_FIRST_IMAGE, L_NEXT_IMAGE, L_LAST_IMAGE |
Notes: (1) If res == 0 and the input resolution field is 0, this will use DefaultInputRes. (2) See comments in convertToPdf().
Definition at line 1172 of file pdfio1.c.
References L_FIRST_IMAGE, L_FLATE_ENCODE, L_G4_ENCODE, L_JP2K_ENCODE, L_JPEG_ENCODE, pixConvertToPdfData(), pixDestroy(), pixReadMem(), and selectDefaultPdfEncoding().
BOXAA* convertNumberedMasksToBoxaa | ( | const char * | dirname, |
const char * | substr, | ||
l_int32 | numpre, | ||
l_int32 | numpost | ||
) |
[in] | dirname | directory name containing mask images |
[in] | substr | [optional] substring filter on filenames; can be null |
[in] | numpre | number of characters in name before number |
[in] | numpost | number of characters in name after number, up to a dot before an extension |
Notes: (1) This is conveniently used to generate the input boxaa for convertSegmentedFilesToPdf(). It guarantees that the boxa will be aligned with the page images, even if some of the boxa are empty.
Definition at line 1540 of file pdfio1.c.
References boxaaCreate(), boxaaInitFull(), boxaaReplaceBoxa(), boxaCreate(), boxaDestroy(), getNumberedPathnamesInDirectory(), L_NOCOPY, pixConnComp(), pixDestroy(), pixRead(), sarrayDestroy(), sarrayGetCount(), and sarrayGetString().
l_ok convertSegmentedFilesToPdf | ( | const char * | dirname, |
const char * | substr, | ||
l_int32 | res, | ||
l_int32 | type, | ||
l_int32 | thresh, | ||
BOXAA * | baa, | ||
l_int32 | quality, | ||
l_float32 | scalefactor, | ||
const char * | title, | ||
const char * | fileout | ||
) |
[in] | dirname | directory name containing images |
[in] | substr | [optional] substring filter on filenames; can be null |
[in] | res | input resolution of all images |
[in] | type | compression type for non-image regions; the image regions are always compressed with L_JPEG_ENCODE |
[in] | thresh | used for converting gray --> 1 bpp with L_G4_ENCODE |
[in] | baa | [optional] boxaa of image regions |
[in] | quality | used for JPEG only; 0 for default (75) |
[in] | scalefactor | scaling factor applied to each image region |
[in] | title | [optional] pdf title; can be null |
[in] | fileout | pdf file of all images |
Notes: (1) If substr is not NULL, only image filenames that contain the substring can be used. If substr == NULL, all files in the directory are used. (2) The files in the directory, after optional filtering by the substring, are lexically sorted in increasing order before concatenation. (3) The images are encoded with G4 if 1 bpp; JPEG if 8 bpp without colormap and many colors, or 32 bpp; FLATE for anything else. (4) The boxaa, if it exists, contains one boxa of "image regions" for each image file. The boxa must be aligned with the sorted set of images. (5) The scalefactor is applied to each image region. It is typically < 1.0, to save bytes in the final pdf, because the resolution is often not critical in non-text regions. (6) If the non-image regions have pixel depth > 1 and the encoding type is G4, they are automatically scaled up by 2x and thresholded. Otherwise, no scaling is performed on them. (7) Note that this function can be used to generate multipage G4 compressed pdf from any input, by using boxaa == NULL and type == L_G4_ENCODE.
Definition at line 1422 of file pdfio1.c.
References boxaaExtendWithInit(), boxaaGetBoxa(), boxaaGetCount(), boxaCreate(), boxaDestroy(), boxaGetCount(), convertToPdfDataSegmented(), getNumberedPathnamesInDirectory(), l_binaryWrite(), l_byteaDestroy(), l_byteaInitFromMem(), L_CLONE, L_NO_COMPACTION, L_NOCOPY, ptraAdd(), ptraConcatenatePdfToData(), ptraCreate(), ptraDestroy(), ptraGetActualCount(), ptraRemove(), sarrayDestroy(), sarrayGetCount(), and sarrayGetString().
l_ok convertToPdf | ( | const char * | filein, |
l_int32 | type, | ||
l_int32 | quality, | ||
const char * | fileout, | ||
l_int32 | x, | ||
l_int32 | y, | ||
l_int32 | res, | ||
const char * | title, | ||
L_PDF_DATA ** | plpd, | ||
l_int32 | position | ||
) |
[in] | filein | input image file – any format |
[in] | type | encoding type (L_JPEG_ENCODE, L_G4_ENCODE, L_FLATE_ENCODE, or L_JP2K_ENCODE) |
[in] | quality | for jpeg: 1-100; 0 for default (75) for jp2k: 27-45; 0 for default (34) |
[in] | fileout | output pdf file; only required on last image on page |
[in] | x,y | location of lower-left corner of image, in pixels, relative to the PostScript origin (0,0) at the lower-left corner of the page |
[in] | res | override the resolution of the input image, in ppi; use 0 to respect the resolution embedded in the input images |
[in] | title | [optional] pdf title; can be null |
[in,out] | plpd | ptr to lpd, which is created on the first invocation and returned until last image is processed, at which time it is destroyed |
[in] | position | in image sequence: L_FIRST_IMAGE, L_NEXT_IMAGE, L_LAST_IMAGE |
Notes: (1) To wrap only one image in pdf, input plpd = NULL, and the value of position will be ignored: convertToPdf(... type, quality, x, y, res, NULL, 0); (2) To wrap multiple images on a single pdf page, this is called once for each successive image. Do it this way: L_PDF_DATA *lpd; convertToPdf(... type, quality, x, y, res, &lpd, L_FIRST_IMAGE); convertToPdf(... type, quality, x, y, res, &lpd, L_NEXT_IMAGE); ... convertToPdf(... type, quality, x, y, res, &lpd, L_LAST_IMAGE); This will write the result to the value of fileout specified in the first call; succeeding values of fileout are ignored. On the last call: the pdf data bytes are computed and written to fileout, lpd is destroyed internally, and the returned value of lpd is null. So the client has nothing to clean up. (3) (a) Set res == 0 to respect the resolution embedded in the image file. If no resolution is embedded, it will be set to the default value. (b) Set res to some other value to override the file resolution. (4) (a) If the input res and the resolution of the output device are equal, the image will be "displayed" at the same size as the original. (b) If the input res is 72, the output device will render the image at 1 pt/pixel. (c) Some possible choices for the default input pix resolution are: 72 ppi Render pix on any output device at one pt/pixel 96 ppi Windows default for generated display images 300 ppi Typical default for scanned images. We choose 300, which is sensible for rendering page images. However, images come from a variety of sources, and some are explicitly created for viewing on a display.
Definition at line 969 of file pdfio1.c.
References convertToPdfData(), l_binaryWrite(), and L_LAST_IMAGE.
l_ok convertToPdfData | ( | const char * | filein, |
l_int32 | type, | ||
l_int32 | quality, | ||
l_uint8 ** | pdata, | ||
size_t * | pnbytes, | ||
l_int32 | x, | ||
l_int32 | y, | ||
l_int32 | res, | ||
const char * | title, | ||
L_PDF_DATA ** | plpd, | ||
l_int32 | position | ||
) |
[in] | filein | input image file – any format |
[in] | type | encoding type (L_JPEG_ENCODE, L_G4_ENCODE, L_FLATE_ENCODE, or L_JP2K_ENCODE) |
[in] | quality | for jpeg: 1-100; 0 for default (75) for jp2k: 27-45; 0 for default (34) |
[out] | pdata | pdf data in memory |
[out] | pnbytes | number of bytes in pdf data |
[in] | x,y | location of lower-left corner of image, in pixels, relative to the PostScript origin (0,0) at the lower-left corner of the page |
[in] | res | override the resolution of the input image, in ppi; use 0 to respect the resolution embedded in the input images |
[in] | title | [optional] pdf title; can be null |
[in,out] | plpd | ptr to lpd, which is created on the first invocation and returned until last image is processed, at which time it is destroyed |
[in] | position | in image sequence: L_FIRST_IMAGE, L_NEXT_IMAGE, L_LAST_IMAGE |
Notes: (1) If res == 0 and the input resolution field is 0, this will use DefaultInputRes. (2) See comments in convertToPdf().
Definition at line 1106 of file pdfio1.c.
References pixConvertToPdfData(), pixDestroy(), and pixRead().
Referenced by convertToPdf().
l_ok convertToPdfDataSegmented | ( | const char * | filein, |
l_int32 | res, | ||
l_int32 | type, | ||
l_int32 | thresh, | ||
BOXA * | boxa, | ||
l_int32 | quality, | ||
l_float32 | scalefactor, | ||
const char * | title, | ||
l_uint8 ** | pdata, | ||
size_t * | pnbytes | ||
) |
[in] | filein | input image file – any format |
[in] | res | input image resolution; typ. 300 ppi; use 0 for default |
[in] | type | compression type for non-image regions; image regions are always compressed with L_JPEG_ENCODE |
[in] | thresh | for converting gray --> 1 bpp with L_G4_ENCODE |
[in] | boxa | [optional] image regions; can be null |
[in] | quality | used for jpeg image regions; 0 for default |
[in] | scalefactor | used for jpeg regions; must be <= 1.0 |
[in] | title | [optional] pdf title; can be null |
[out] | pdata | pdf data in memory |
[out] | pnbytes | number of bytes in pdf data |
Notes: (1) If there are no image regions, set boxa == NULL; quality and scalefactor are ignored. (2) Typically, scalefactor is < 1.0. The image regions are
Definition at line 1766 of file pdfio1.c.
References L_FLATE_ENCODE, L_G4_ENCODE, L_JPEG_ENCODE, pixConvertToPdfDataSegmented(), pixDestroy(), and pixRead().
Referenced by convertSegmentedFilesToPdf().
l_ok convertToPdfSegmented | ( | const char * | filein, |
l_int32 | res, | ||
l_int32 | type, | ||
l_int32 | thresh, | ||
BOXA * | boxa, | ||
l_int32 | quality, | ||
l_float32 | scalefactor, | ||
const char * | title, | ||
const char * | fileout | ||
) |
[in] | filein | input image file – any format |
[in] | res | input image resolution; typ. 300 ppi; use 0 for default |
[in] | type | compression type for non-image regions; image regions are always compressed with L_JPEG_ENCODE |
[in] | thresh | for converting gray --> 1 bpp with L_G4_ENCODE |
[in] | boxa | [optional] of image regions; can be null |
[in] | quality | used for jpeg image regions; 0 for default |
[in] | scalefactor | used for jpeg regions; must be <= 1.0 |
[in] | title | [optional] pdf title; can be null |
[in] | fileout | output pdf file |
Notes: (1) If there are no image regions, set boxa == NULL; quality and scalefactor are ignored. (2) Typically, scalefactor is < 1.0, because the image regions can be rendered at a lower resolution (for better compression) than the text regions. If scalefactor == 0, we use 1.0. If the input image is 1 bpp and scalefactor < 1.0, we use scaleToGray() to downsample the image regions to gray before compressing them. (3) If the compression type for non-image regions is L_G4_ENCODE and bpp > 1, the image is upscaled 2x and thresholded to 1 bpp. That is the only situation where thresh is used. (4) The parameter quality is only used for image regions. If type == L_JPEG_ENCODE, default jpeg quality (75) is used for the non-image regions. (5) Processing matrix for non-image regions. Input G4 JPEG FLATE ----------|--------------------------------------------------- 1 bpp | 1x, 1 bpp 1x flate, 1 bpp 1x, 1 bpp | cmap | 2x, 1 bpp 1x flate, cmap 1x, cmap | 2,4 bpp | 2x, 1 bpp 1x flate 1x, 2,4 bpp no cmap | 2,4 bpp | 8,32 bpp | 2x, 1 bpp 1x (jpeg) 1x, 8,32 bpp no cmap | 8,32 bpp Summary: (a) if G4 is requested, G4 is used, with 2x upscaling for all cases except 1 bpp. (b) if JPEG is requested, use flate encoding for all cases except 8 bpp without cmap and 32 bpp (rgb). (c) if FLATE is requested, use flate with no transformation of the raster data. (6) Calling options/sequence for these functions: file --> file (convertToPdfSegmented) pix --> file (pixConvertToPdfSegmented) pix --> data (pixConvertToPdfDataSegmented) file --> data (convertToPdfDataSegmented) pix --> data (pixConvertToPdfDataSegmented)
Definition at line 1647 of file pdfio1.c.
References L_FLATE_ENCODE, L_G4_ENCODE, L_JPEG_ENCODE, pixConvertToPdfSegmented(), pixDestroy(), and pixRead().
l_ok convertUnscaledFilesToPdf | ( | const char * | dirname, |
const char * | substr, | ||
const char * | title, | ||
const char * | fileout | ||
) |
[in] | dirname | directory name containing images |
[in] | substr | [optional] substring filter on filenames; can be null |
[in] | title | [optional] pdf title; can be null |
[in] | fileout | pdf file of all images |
Notes: (1) If substr is not NULL, only image filenames that contain the substring can be used. If substr == NULL, all files in the directory are used. (2) The files in the directory, after optional filtering by the substring, are lexically sorted in increasing order before concatenation. (3) This is very fast for jpeg, jp2k and some png files, because the compressed data is wrapped up and concatenated. For other types of png, the images must be read and recompressed.
Definition at line 527 of file pdfio1.c.
References getSortedPathnamesInDirectory(), saConvertUnscaledFilesToPdf(), and sarrayDestroy().
l_ok convertUnscaledToPdfData | ( | const char * | fname, |
const char * | title, | ||
l_uint8 ** | pdata, | ||
size_t * | pnbytes | ||
) |
[in] | fname | of image file in all formats |
[in] | title | [optional] pdf title; can be null |
[out] | pdata | output pdf data for image |
[out] | pnbytes | size of output pdf data |
Notes: (1) This is very fast for jpeg, jp2k and some png files, because the compressed data is wrapped up and concatenated. For other types of png, the images must be read and recompressed.
Definition at line 681 of file pdfio1.c.
References findFileFormat().
Referenced by saConvertUnscaledFilesToPdfData().
l_ok pixaConvertToPdf | ( | PIXA * | pixa, |
l_int32 | res, | ||
l_float32 | scalefactor, | ||
l_int32 | type, | ||
l_int32 | quality, | ||
const char * | title, | ||
const char * | fileout | ||
) |
[in] | pixa | containing images all at the same resolution |
[in] | res | override the resolution of each input image, in ppi; use 0 to respect the resolution embedded in the input images |
[in] | scalefactor | scaling factor applied to each image; > 0.0 |
[in] | type | encoding type (L_JPEG_ENCODE, L_G4_ENCODE, L_FLATE_ENCODE, L_JP2K_ENCODE, or L_DEFAULT_ENCODE for default) |
[in] | quality | for jpeg: 1-100; 0 for default (75) for jp2k: 27-45; 0 for default (34) |
[in] | title | [optional] pdf title; can be null |
[in] | fileout | pdf file of all images |
Notes: (1) The images are encoded with G4 if 1 bpp; JPEG if 8 bpp without colormap and many colors, or 32 bpp; FLATE for anything else. (2) The scalefactor must be > 0.0; otherwise it is set to 1.0. (3) Specifying one of the three encoding types for type forces all images to be compressed with that type. Use 0 to have the type determined for each image based on depth and whether or not it has a colormap.
Definition at line 756 of file pdfio1.c.
References l_binaryWrite(), and pixaConvertToPdfData().
Referenced by convertTiffMultipageToPdf(), pixaCompareInPdf(), pixaSelectToPdf(), and pixCompareWithTranslation().
l_ok pixaConvertToPdfData | ( | PIXA * | pixa, |
l_int32 | res, | ||
l_float32 | scalefactor, | ||
l_int32 | type, | ||
l_int32 | quality, | ||
const char * | title, | ||
l_uint8 ** | pdata, | ||
size_t * | pnbytes | ||
) |
[in] | pixa | containing images all at the same resolution |
[in] | res | input resolution of all images |
[in] | scalefactor | scaling factor applied to each image; > 0.0; <50 |
[in] | type | encoding type (L_JPEG_ENCODE, L_G4_ENCODE, L_FLATE_ENCODE, L_JP2K_ENCODE, or L_DEFAULT_ENCODE for default) |
[in] | quality | for jpeg: 1-100; 0 for default (75) for jp2k: 27-45; 0 for default (34) |
[in] | title | [optional] pdf title; can be null |
[out] | pdata | output pdf data of all images |
[out] | pnbytes | size of output pdf data |
Notes: (1) See pixaConvertToPdf().
Definition at line 808 of file pdfio1.c.
References l_byteaDestroy(), l_byteaInitFromMem(), L_CLONE, L_DEFAULT_ENCODE, L_FLATE_ENCODE, L_G4_ENCODE, L_JP2K_ENCODE, L_JPEG_ENCODE, L_NO_COMPACTION, pixaGetCount(), pixaGetPix(), pixClone(), pixConvertToPdfData(), pixDestroy(), pixScale(), ptraAdd(), ptraConcatenatePdfToData(), ptraCreate(), ptraDestroy(), ptraGetActualCount(), ptraRemove(), and selectDefaultPdfEncoding().
Referenced by pixaConvertToPdf().
l_ok pixConvertToPdf | ( | PIX * | pix, |
l_int32 | type, | ||
l_int32 | quality, | ||
const char * | fileout, | ||
l_int32 | x, | ||
l_int32 | y, | ||
l_int32 | res, | ||
const char * | title, | ||
L_PDF_DATA ** | plpd, | ||
l_int32 | position | ||
) |
[in] | pix | |
[in] | type | encoding type (L_JPEG_ENCODE, L_G4_ENCODE, L_FLATE_ENCODE, L_JP2K_ENCODE) |
[in] | quality | for jpeg: 1-100; 0 for default (75) for jp2k: 27-45; 0 for default (34) |
[in] | fileout | output pdf file; only required on last image on page |
[in] | x,y | location of lower-left corner of image, in pixels, relative to the PostScript origin (0,0) at the lower-left corner of the page |
[in] | res | override the resolution of the input image, in ppi; use 0 to respect the resolution embedded in the input images |
[in] | title | [optional] pdf title; can be null |
[in,out] | plpd | ptr to lpd, which is created on the first invocation and returned until last image is processed, at which time it is destroyed |
[in] | position | in image sequence: L_FIRST_IMAGE, L_NEXT_IMAGE, L_LAST_IMAGE |
Notes: (1) If res == 0 and the input resolution field is 0, this will use DefaultInputRes. (2) This only writes data to fileout if it is the last image to be written on the page. (3) See comments in convertToPdf().
Definition at line 1248 of file pdfio1.c.
References l_binaryWrite(), L_LAST_IMAGE, and pixConvertToPdfData().
Referenced by convertImageDataToPdf().
l_ok pixConvertToPdfDataSegmented | ( | PIX * | pixs, |
l_int32 | res, | ||
l_int32 | type, | ||
l_int32 | thresh, | ||
BOXA * | boxa, | ||
l_int32 | quality, | ||
l_float32 | scalefactor, | ||
const char * | title, | ||
l_uint8 ** | pdata, | ||
size_t * | pnbytes | ||
) |
pixConvertToPdfDataSegmented()
[in] | pixs | any depth, cmap OK |
[in] | res | input image resolution; typ. 300 ppi; use 0 for default |
[in] | type | compression type for non-image regions; image regions are always compressed with L_JPEG_ENCODE |
[in] | thresh | for converting gray --> 1 bpp with L_G4_ENCODE |
[in] | boxa | [optional] of image regions; can be null |
[in] | quality | used for jpeg image regions; 0 for default |
[in] | scalefactor | used for jpeg regions; must be <= 1.0 |
[in] | title | [optional] pdf title; can be null |
[out] | pdata | pdf data in memory |
[out] | pnbytes | number of bytes in pdf data |
Notes: (1) See convertToPdfSegmented() for details.
Definition at line 1830 of file pdfio1.c.
References L_FLATE_ENCODE, L_G4_ENCODE, and L_JPEG_ENCODE.
Referenced by convertToPdfDataSegmented(), and pixConvertToPdfSegmented().
l_ok pixConvertToPdfSegmented | ( | PIX * | pixs, |
l_int32 | res, | ||
l_int32 | type, | ||
l_int32 | thresh, | ||
BOXA * | boxa, | ||
l_int32 | quality, | ||
l_float32 | scalefactor, | ||
const char * | title, | ||
const char * | fileout | ||
) |
[in] | pixs | any depth, cmap OK |
[in] | res | input image resolution; typ. 300 ppi; use 0 for default |
[in] | type | compression type for non-image regions; image regions are always compressed with L_JPEG_ENCODE |
[in] | thresh | for converting gray --> 1 bpp with L_G4_ENCODE |
[in] | boxa | [optional] of image regions; can be null |
[in] | quality | used for jpeg image regions; 0 for default |
[in] | scalefactor | used for jpeg regions; must be <= 1.0 |
[in] | title | [optional] pdf title; can be null |
[in] | fileout | output pdf file |
Notes: (1) See convertToPdfSegmented() for details.
Definition at line 1704 of file pdfio1.c.
References l_binaryWrite(), L_FLATE_ENCODE, L_G4_ENCODE, L_JPEG_ENCODE, and pixConvertToPdfDataSegmented().
Referenced by convertToPdfSegmented().
l_ok pixWriteMemPdf | ( | l_uint8 ** | pdata, |
size_t * | pnbytes, | ||
PIX * | pix, | ||
l_int32 | res, | ||
const char * | title | ||
) |
[out] | pdata | pdf as byte array |
[out] | pnbytes | number of bytes in pdf array |
[in] | pix | all depths, cmap OK |
[in] | res | override the resolution of the input image, in ppi; use 0 to respect the res embedded in the input |
[in] | title | [optional] pdf title; can be null |
Notes: (1) This is the simplest interface for writing a single image with pdf encoding to memory. It uses G4 encoding for 1 bpp, and makes a guess whether to use JPEG or FLATE encoding for everything else.
Definition at line 1351 of file pdfio1.c.
References pixConvertToPdfData(), and selectDefaultPdfEncoding().
Referenced by pixWriteStreamPdf().
l_ok pixWriteStreamPdf | ( | FILE * | fp, |
PIX * | pix, | ||
l_int32 | res, | ||
const char * | title | ||
) |
[in] | fp | file stream opened for writing |
[in] | pix | all depths, cmap OK |
[in] | res | override the resolution of the input image, in ppi; use 0 to respect the resolution embedded in the input |
[in] | title | [optional] pdf title; can be null |
Notes: (1) This is the simplest interface for writing a single image with pdf encoding to a stream. It uses G4 encoding for 1 bpp, JPEG encoding for 8 bpp (no cmap) and 32 bpp, and FLATE encoding for everything else.
Definition at line 1305 of file pdfio1.c.
References pixWriteMemPdf().
l_ok ptraConcatenatePdf | ( | L_PTRA * | pa, |
const char * | fileout | ||
) |
[in] | pa | array of pdf strings, each for a single-page pdf file |
[in] | fileout | concatenated pdf file |
Notes: (1) This only works with leptonica-formatted single-page pdf files.
Definition at line 2060 of file pdfio1.c.
References l_binaryWrite(), and ptraConcatenatePdfToData().
l_ok saConcatenatePdf | ( | SARRAY * | sa, |
const char * | fileout | ||
) |
[in] | sa | string array of pathnames for single-page pdf files |
[in] | fileout | concatenated pdf file |
Notes: (1) This only works with leptonica-formatted single-page pdf files.
Definition at line 2026 of file pdfio1.c.
References l_binaryWrite(), and saConcatenatePdfToData().
Referenced by concatenatePdf().
l_ok saConcatenatePdfToData | ( | SARRAY * | sa, |
l_uint8 ** | pdata, | ||
size_t * | pnbytes | ||
) |
[in] | sa | string array of pathnames for single-page pdf files |
[out] | pdata | concatenated pdf data in memory |
[out] | pnbytes | number of bytes in pdf data |
Notes: (1) This only works with leptonica-formatted single-page pdf files.
Definition at line 2142 of file pdfio1.c.
References l_byteaDestroy(), l_byteaInitFromFile(), L_NO_COMPACTION, L_NOCOPY, ptraAdd(), ptraConcatenatePdfToData(), ptraCreate(), ptraDestroy(), ptraGetActualCount(), ptraRemove(), sarrayGetCount(), and sarrayGetString().
Referenced by concatenatePdfToData(), and saConcatenatePdf().
l_ok saConvertFilesToPdf | ( | SARRAY * | sa, |
l_int32 | res, | ||
l_float32 | scalefactor, | ||
l_int32 | type, | ||
l_int32 | quality, | ||
const char * | title, | ||
const char * | fileout | ||
) |
[in] | sa | string array of pathnames for images |
[in] | res | input resolution of all images |
[in] | scalefactor | scaling factor applied to each image; > 0.0 |
[in] | type | encoding type (L_JPEG_ENCODE, L_G4_ENCODE, L_FLATE_ENCODE, L_JP2K_ENCODE or L_DEFAULT_ENCODE for default) |
[in] | quality | for jpeg: 1-100; 0 for default (75) for jp2k: 27-45; 0 for default (34) |
[in] | title | [optional] pdf title; can be null |
[in] | fileout | pdf file of all images |
Notes: (1) See convertFilesToPdf().
Definition at line 299 of file pdfio1.c.
References l_binaryWrite(), and saConvertFilesToPdfData().
Referenced by convertFilesToPdf().
l_ok saConvertFilesToPdfData | ( | SARRAY * | sa, |
l_int32 | res, | ||
l_float32 | scalefactor, | ||
l_int32 | type, | ||
l_int32 | quality, | ||
const char * | title, | ||
l_uint8 ** | pdata, | ||
size_t * | pnbytes | ||
) |
[in] | sa | string array of pathnames for images |
[in] | res | input resolution of all images |
[in] | scalefactor | scaling factor applied to each image; > 0.0 |
[in] | type | encoding type (L_JPEG_ENCODE, L_G4_ENCODE, L_FLATE_ENCODE, L_JP2K_ENCODE or L_DEFAULT_ENCODE for default) |
[in] | quality | for jpeg: 1-100; 0 for default (75) for jp2k: 27-45; 0 for default (34) |
[in] | title | [optional] pdf title; can be null |
[out] | pdata | output pdf data (of all images |
[out] | pnbytes | size of output pdf data |
Notes: (1) See convertFilesToPdf().
Definition at line 351 of file pdfio1.c.
References l_byteaDestroy(), l_byteaInitFromMem(), L_DEFAULT_ENCODE, L_FLATE_ENCODE, L_G4_ENCODE, L_JP2K_ENCODE, L_JPEG_ENCODE, L_NO_COMPACTION, L_NOCOPY, lept_stderr(), pixClone(), pixConvertToPdfData(), pixDestroy(), pixRead(), pixScale(), ptraAdd(), ptraConcatenatePdfToData(), ptraCreate(), ptraDestroy(), ptraGetActualCount(), ptraRemove(), sarrayGetCount(), sarrayGetString(), and selectDefaultPdfEncoding().
Referenced by saConvertFilesToPdf().
l_ok saConvertUnscaledFilesToPdf | ( | SARRAY * | sa, |
const char * | title, | ||
const char * | fileout | ||
) |
[in] | sa | string array of pathnames for images |
[in] | title | [optional] pdf title; can be null |
[in] | fileout | pdf file of all images |
Notes: (1) See convertUnscaledFilesToPdf().
Definition at line 562 of file pdfio1.c.
References l_binaryWrite(), and saConvertUnscaledFilesToPdfData().
Referenced by convertUnscaledFilesToPdf().
l_ok saConvertUnscaledFilesToPdfData | ( | SARRAY * | sa, |
const char * | title, | ||
l_uint8 ** | pdata, | ||
size_t * | pnbytes | ||
) |
saConvertUnscaledFilesToPdfData()
[in] | sa | string array of pathnames for image files |
[in] | title | [optional] pdf title; can be null |
[out] | pdata | output pdf data (of all images) |
[out] | pnbytes | size of output pdf data |
Notes: (1) This is very fast for jpeg, jp2k and some png files, because the compressed data is wrapped up and concatenated. For other types of png, the images must be read and recompressed.
Definition at line 604 of file pdfio1.c.
References convertUnscaledToPdfData(), l_byteaDestroy(), l_byteaInitFromMem(), L_NO_COMPACTION, L_NOCOPY, lept_stderr(), ptraAdd(), ptraConcatenatePdfToData(), ptraCreate(), ptraDestroy(), ptraGetActualCount(), ptraRemove(), sarrayGetCount(), and sarrayGetString().
Referenced by saConvertUnscaledFilesToPdf().
l_ok selectDefaultPdfEncoding | ( | PIX * | pix, |
l_int32 * | ptype | ||
) |
[in] | pix | |
[out] | ptype | L_G4_ENCODE, L_JPEG_ENCODE, L_FLATE_ENCODE |
Notes: (1) This attempts to choose an encoding for the pix that results in the smallest file, assuming that if jpeg encoded, it will use quality = 75. The decision is approximate, in that (a) all colormapped images will be losslessly encoded with gzip (flate), and (b) an image with less than about 20 colors is likely to be smaller if flate encoded than if encoded as a jpeg (dct). For example, an image made by pixScaleToGray3() will have 10 colors, and flate encoding will give about twice the compression as jpeg with quality = 75.
Definition at line 464 of file pdfio1.c.
References L_FLATE_ENCODE, and pixGetDimensions().
Referenced by convertImageDataToPdf(), convertImageDataToPdfData(), pixaConvertToPdfData(), pixConvertToPdfData(), pixGenerateCIData(), pixWriteMemPdf(), and saConvertFilesToPdfData().