mirror/yacreader
1
0
Fork 0
mirror of https://github.com/YACReader/yacreader synced 2025-07-24 07:55:02 -04:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update pdfium for windows

Browse Source
This commit is contained in:
Luis Ángel San Martín
2024-10-12 10:15:43 +02:00
parent b7b9e9561c
commit 442307cc65
32 changed files with 5351 additions and 2630 deletions
Download Patch File Download Diff File Expand all files Collapse all files

370
dependencies/pdfium/win/public/fpdf_text.h vendored
View File

@ -1,4 +1,4 @@
// Copyright 2014 PDFium Authors. All rights reserved.
// Copyright 2014 The PDFium Authors
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
@ -7,6 +7,7 @@
#ifndef PUBLIC_FPDF_TEXT_H_
#define PUBLIC_FPDF_TEXT_H_
// clang-format off
// NOLINTNEXTLINE(build/include)
#include "fpdfview.h"
@ -19,7 +20,7 @@ extern "C" {
// Prepare information about all characters in a page.
// Parameters:
// page - Handle to the page. Returned by FPDF_LoadPage function
// (in FPDFVIEW module).
// (in FPDFVIEW module).
// Return value:
// A handle to the text page information structure.
// NULL if something goes wrong.
@ -34,7 +35,7 @@ FPDF_EXPORT FPDF_TEXTPAGE FPDF_CALLCONV FPDFText_LoadPage(FPDF_PAGE page);
// structure.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// Return Value:
// None.
//
@ -44,7 +45,7 @@ FPDF_EXPORT void FPDF_CALLCONV FPDFText_ClosePage(FPDF_TEXTPAGE text_page);
// Get number of characters in a page.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// Return value:
// Number of characters in the page. Return -1 for error.
// Generated characters, like additional space characters, new line
@ -62,7 +63,7 @@ FPDF_EXPORT int FPDF_CALLCONV FPDFText_CountChars(FPDF_TEXTPAGE text_page);
// Get Unicode of a character in a page.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// Return value:
// The Unicode of the particular character.
@ -73,16 +74,76 @@ FPDF_EXPORT int FPDF_CALLCONV FPDFText_CountChars(FPDF_TEXTPAGE text_page);
FPDF_EXPORT unsigned int FPDF_CALLCONV
FPDFText_GetUnicode(FPDF_TEXTPAGE text_page, int index);
// Experimental API.
// Function: FPDFText_GetTextObject
// Get the FPDF_PAGEOBJECT associated with a given character.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// Return value:
// The associated text object for the character at |index|, or NULL on
// error. The returned text object, if non-null, is of type
// |FPDF_PAGEOBJ_TEXT|. The caller does not own the returned object.
//
FPDF_EXPORT FPDF_PAGEOBJECT FPDF_CALLCONV
FPDFText_GetTextObject(FPDF_TEXTPAGE text_page, int index);
// Experimental API.
// Function: FPDFText_IsGenerated
// Get if a character in a page is generated by PDFium.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// Return value:
// 1 if the character is generated by PDFium.
// 0 if the character is not generated by PDFium.
// -1 if there was an error.
//
FPDF_EXPORT int FPDF_CALLCONV
FPDFText_IsGenerated(FPDF_TEXTPAGE text_page, int index);
// Experimental API.
// Function: FPDFText_IsHyphen
// Get if a character in a page is a hyphen.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// Return value:
// 1 if the character is a hyphen.
// 0 if the character is not a hyphen.
// -1 if there was an error.
//
FPDF_EXPORT int FPDF_CALLCONV
FPDFText_IsHyphen(FPDF_TEXTPAGE text_page, int index);
// Experimental API.
// Function: FPDFText_HasUnicodeMapError
// Get if a character in a page has an invalid unicode mapping.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// Return value:
// 1 if the character has an invalid unicode mapping.
// 0 if the character has no known unicode mapping issues.
// -1 if there was an error.
//
FPDF_EXPORT int FPDF_CALLCONV
FPDFText_HasUnicodeMapError(FPDF_TEXTPAGE text_page, int index);
// Function: FPDFText_GetFontSize
// Get the font size of a particular character.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// Return value:
// The font size of the particular character, measured in points (about
// 1/72 inch).
// This is the typographic size of the font (so called "em size").
// 1/72 inch). This is the typographic size of the font (so called
// "em size").
//
FPDF_EXPORT double FPDF_CALLCONV FPDFText_GetFontSize(FPDF_TEXTPAGE text_page,
int index);
@ -92,19 +153,20 @@ FPDF_EXPORT double FPDF_CALLCONV FPDFText_GetFontSize(FPDF_TEXTPAGE text_page,
// Get the font name and flags of a particular character.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// buffer - A buffer receiving the font name.
// buflen - The length of |buffer| in bytes.
// flags - Optional pointer to an int receiving the font flags.
// These flags should be interpreted per PDF spec 1.7 Section 5.7.1
// Font Descriptor Flags.
// These flags should be interpreted per PDF spec 1.7
// Section 5.7.1 Font Descriptor Flags.
// Return value:
// On success, return the length of the font name, including the
// trailing NUL character, in bytes. If this length is less than or
// equal to |length|, |buffer| is set to the font name, |flags| is
// set to the font flags. |buffer| is in UTF-8 encoding. Return 0 on
// failure.
//
FPDF_EXPORT unsigned long FPDF_CALLCONV
FPDFText_GetFontInfo(FPDF_TEXTPAGE text_page,
int index,
@ -112,20 +174,104 @@ FPDFText_GetFontInfo(FPDF_TEXTPAGE text_page,
unsigned long buflen,
int* flags);
// Experimental API.
// Function: FPDFText_GetFontWeight
// Get the font weight of a particular character.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// Return value:
// On success, return the font weight of the particular character. If
// |text_page| is invalid, if |index| is out of bounds, or if the
// character's text object is undefined, return -1.
//
FPDF_EXPORT int FPDF_CALLCONV FPDFText_GetFontWeight(FPDF_TEXTPAGE text_page,
int index);
// Experimental API.
// Function: FPDFText_GetFillColor
// Get the fill color of a particular character.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// R - Pointer to an unsigned int number receiving the
// red value of the fill color.
// G - Pointer to an unsigned int number receiving the
// green value of the fill color.
// B - Pointer to an unsigned int number receiving the
// blue value of the fill color.
// A - Pointer to an unsigned int number receiving the
// alpha value of the fill color.
// Return value:
// Whether the call succeeded. If false, |R|, |G|, |B| and |A| are
// unchanged.
//
FPDF_EXPORT FPDF_BOOL FPDF_CALLCONV
FPDFText_GetFillColor(FPDF_TEXTPAGE text_page,
int index,
unsigned int* R,
unsigned int* G,
unsigned int* B,
unsigned int* A);
// Experimental API.
// Function: FPDFText_GetStrokeColor
// Get the stroke color of a particular character.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// R - Pointer to an unsigned int number receiving the
// red value of the stroke color.
// G - Pointer to an unsigned int number receiving the
// green value of the stroke color.
// B - Pointer to an unsigned int number receiving the
// blue value of the stroke color.
// A - Pointer to an unsigned int number receiving the
// alpha value of the stroke color.
// Return value:
// Whether the call succeeded. If false, |R|, |G|, |B| and |A| are
// unchanged.
//
FPDF_EXPORT FPDF_BOOL FPDF_CALLCONV
FPDFText_GetStrokeColor(FPDF_TEXTPAGE text_page,
int index,
unsigned int* R,
unsigned int* G,
unsigned int* B,
unsigned int* A);
// Experimental API.
// Function: FPDFText_GetCharAngle
// Get character rotation angle.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// Return Value:
// On success, return the angle value in radian. Value will always be
// greater or equal to 0. If |text_page| is invalid, or if |index| is
// out of bounds, then return -1.
//
FPDF_EXPORT float FPDF_CALLCONV FPDFText_GetCharAngle(FPDF_TEXTPAGE text_page,
int index);
// Function: FPDFText_GetCharBox
// Get bounding box of a particular character.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// left - Pointer to a double number receiving left position
// of the character box.
// of the character box.
// right - Pointer to a double number receiving right position
// of the character box.
// of the character box.
// bottom - Pointer to a double number receiving bottom position
// of the character box.
// of the character box.
// top - Pointer to a double number receiving top position of
// the character box.
// the character box.
// Return Value:
// On success, return TRUE and fill in |left|, |right|, |bottom|, and
// |top|. If |text_page| is invalid, or if |index| is out of bounds,
@ -140,16 +286,54 @@ FPDF_EXPORT FPDF_BOOL FPDF_CALLCONV FPDFText_GetCharBox(FPDF_TEXTPAGE text_page,
double* bottom,
double* top);
// Experimental API.
// Function: FPDFText_GetLooseCharBox
// Get a "loose" bounding box of a particular character, i.e., covering
// the entire glyph bounds, without taking the actual glyph shape into
// account.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// rect - Pointer to a FS_RECTF receiving the character box.
// Return Value:
// On success, return TRUE and fill in |rect|. If |text_page| is
// invalid, or if |index| is out of bounds, then return FALSE, and the
// |rect| out parameter remains unmodified.
// Comments:
// All positions are measured in PDF "user space".
//
FPDF_EXPORT FPDF_BOOL FPDF_CALLCONV
FPDFText_GetLooseCharBox(FPDF_TEXTPAGE text_page, int index, FS_RECTF* rect);
// Experimental API.
// Function: FPDFText_GetMatrix
// Get the effective transformation matrix for a particular character.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage().
// index - Zero-based index of the character.
// matrix - Pointer to a FS_MATRIX receiving the transformation
// matrix.
// Return Value:
// On success, return TRUE and fill in |matrix|. If |text_page| is
// invalid, or if |index| is out of bounds, or if |matrix| is NULL,
// then return FALSE, and |matrix| remains unmodified.
//
FPDF_EXPORT FPDF_BOOL FPDF_CALLCONV FPDFText_GetMatrix(FPDF_TEXTPAGE text_page,
int index,
FS_MATRIX* matrix);
// Function: FPDFText_GetCharOrigin
// Get origin of a particular character.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// index - Zero-based index of the character.
// x - Pointer to a double number receiving x coordinate of
// the character origin.
// the character origin.
// y - Pointer to a double number receiving y coordinate of
// the character origin.
// the character origin.
// Return Value:
// Whether the call succeeded. If false, x and y are unchanged.
// Comments:
@ -166,18 +350,17 @@ FPDFText_GetCharOrigin(FPDF_TEXTPAGE text_page,
// page.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// x - X position in PDF "user space".
// y - Y position in PDF "user space".
// xTolerance - An x-axis tolerance value for character hit
// detection, in point unit.
// detection, in point units.
// yTolerance - A y-axis tolerance value for character hit
// detection, in point unit.
// detection, in point units.
// Return Value:
// The zero-based index of the character at, or nearby the point (x,y).
// If there is no character at or nearby the point, return value will
// be -1.
// If an error occurs, -3 will be returned.
// be -1. If an error occurs, -3 will be returned.
//
FPDF_EXPORT int FPDF_CALLCONV
FPDFText_GetCharIndexAtPos(FPDF_TEXTPAGE text_page,
@ -190,18 +373,21 @@ FPDFText_GetCharIndexAtPos(FPDF_TEXTPAGE text_page,
// Extract unicode text string from the page.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// start_index - Index for the start characters.
// count - Number of characters to be extracted.
// count - Number of UCS-2 values to be extracted.
// result - A buffer (allocated by application) receiving the
// extracted unicodes.
// The size of the buffer must be able to hold the
// number of characters plus a terminator.
// extracted UCS-2 values. The buffer must be able to
// hold `count` UCS-2 values plus a terminator.
// Return Value:
// Number of characters written into the result buffer, including the
// trailing terminator.
// Comments:
// This function ignores characters without unicode information.
// This function ignores characters without UCS-2 representations.
// It considers all characters on the page, even those that are not
// visible when the page has a cropbox. To filter out the characters
// outside of the cropbox, use FPDF_GetPageBoundingBox() and
// FPDFText_GetCharBox().
//
FPDF_EXPORT int FPDF_CALLCONV FPDFText_GetText(FPDF_TEXTPAGE text_page,
int start_index,
@ -209,22 +395,22 @@ FPDF_EXPORT int FPDF_CALLCONV FPDFText_GetText(FPDF_TEXTPAGE text_page,
unsigned short* result);
// Function: FPDFText_CountRects
// Count number of rectangular areas occupied by a segment of texts.
// Counts number of rectangular areas occupied by a segment of text,
// and caches the result for subsequent FPDFText_GetRect() calls.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// start_index - Index for the start characters.
// count - Number of characters.
// Returned by FPDFText_LoadPage function.
// start_index - Index for the start character.
// count - Number of characters, or -1 for all remaining.
// Return value:
// Number of rectangles. Zero for error.
// Number of rectangles, 0 if text_page is null, or -1 on bad
// start_index.
// Comments:
// This function, along with FPDFText_GetRect can be used by
// applications to detect the position
// on the page for a text segment, so proper areas can be highlighted
// or something.
// FPDFTEXT will automatically merge small character boxes into bigger
// one if those characters
// are on the same line and use same font settings.
// applications to detect the position on the page for a text segment,
// so proper areas can be highlighted. The FPDFText_* functions will
// automatically merge small character boxes into bigger one if those
// characters are on the same line and use same font settings.
//
FPDF_EXPORT int FPDF_CALLCONV FPDFText_CountRects(FPDF_TEXTPAGE text_page,
int start_index,
@ -235,16 +421,16 @@ FPDF_EXPORT int FPDF_CALLCONV FPDFText_CountRects(FPDF_TEXTPAGE text_page,
// FPDFText_CountRects.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// rect_index - Zero-based index for the rectangle.
// left - Pointer to a double value receiving the rectangle
// left boundary.
// left boundary.
// top - Pointer to a double value receiving the rectangle
// top boundary.
// top boundary.
// right - Pointer to a double value receiving the rectangle
// right boundary.
// right boundary.
// bottom - Pointer to a double value receiving the rectangle
// bottom boundary.
// bottom boundary.
// Return Value:
// On success, return TRUE and fill in |left|, |top|, |right|, and
// |bottom|. If |text_page| is invalid then return FALSE, and the out
@ -263,27 +449,25 @@ FPDF_EXPORT FPDF_BOOL FPDF_CALLCONV FPDFText_GetRect(FPDF_TEXTPAGE text_page,
// Extract unicode text within a rectangular boundary on the page.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// left - Left boundary.
// top - Top boundary.
// right - Right boundary.
// bottom - Bottom boundary.
// buffer - A unicode buffer.
// buflen - Number of characters (not bytes) for the buffer,
// excluding an additional terminator.
// buffer - Caller-allocated buffer to receive UTF-16 values.
// buflen - Number of UTF-16 values (not bytes) that `buffer`
// is capable of holding.
// Return Value:
// If buffer is NULL or buflen is zero, return number of characters
// (not bytes) of text present within
// the rectangle, excluding a terminating NUL. Generally you should
// pass a buffer at least one larger
// than this if you want a terminating NUL, which will be provided if
// space is available.
// Otherwise, return number of characters copied into the buffer,
// including the terminating NUL
// when space for it is available.
// If buffer is NULL or buflen is zero, return number of UTF-16
// values (not bytes) of text present within the rectangle, excluding
// a terminating NUL. Generally you should pass a buffer at least one
// larger than this if you want a terminating NUL, which will be
// provided if space is available. Otherwise, return number of UTF-16
// values copied into the buffer, including the terminating NUL when
// space for it is available.
// Comment:
// If the buffer is too small, as much text as will fit is copied into
// it.
// it. May return a split surrogate in that case.
//
FPDF_EXPORT int FPDF_CALLCONV FPDFText_GetBoundedText(FPDF_TEXTPAGE text_page,
double left,
@ -306,7 +490,7 @@ FPDF_EXPORT int FPDF_CALLCONV FPDFText_GetBoundedText(FPDF_TEXTPAGE text_page,
// Start a search.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// findwhat - A unicode match pattern.
// flags - Option flags.
// start_index - Start from this character. -1 for end of the page.
@ -324,7 +508,7 @@ FPDFText_FindStart(FPDF_TEXTPAGE text_page,
// Search in the direction from page start to end.
// Parameters:
// handle - A search context handle returned by
// FPDFText_FindStart.
// FPDFText_FindStart.
// Return Value:
// Whether a match is found.
//
@ -334,7 +518,7 @@ FPDF_EXPORT FPDF_BOOL FPDF_CALLCONV FPDFText_FindNext(FPDF_SCHHANDLE handle);
// Search in the direction from page end to start.
// Parameters:
// handle - A search context handle returned by
// FPDFText_FindStart.
// FPDFText_FindStart.
// Return Value:
// Whether a match is found.
//
@ -344,7 +528,7 @@ FPDF_EXPORT FPDF_BOOL FPDF_CALLCONV FPDFText_FindPrev(FPDF_SCHHANDLE handle);
// Get the starting character index of the search result.
// Parameters:
// handle - A search context handle returned by
// FPDFText_FindStart.
// FPDFText_FindStart.
// Return Value:
// Index for the starting character.
//
@ -354,7 +538,7 @@ FPDF_EXPORT int FPDF_CALLCONV FPDFText_GetSchResultIndex(FPDF_SCHHANDLE handle);
// Get the number of matched characters in the search result.
// Parameters:
// handle - A search context handle returned by
// FPDFText_FindStart.
// FPDFText_FindStart.
// Return Value:
// Number of matched characters.
//
@ -364,7 +548,7 @@ FPDF_EXPORT int FPDF_CALLCONV FPDFText_GetSchCount(FPDF_SCHHANDLE handle);
// Release a search context.
// Parameters:
// handle - A search context handle returned by
// FPDFText_FindStart.
// FPDFText_FindStart.
// Return Value:
// None.
//
@ -374,22 +558,18 @@ FPDF_EXPORT void FPDF_CALLCONV FPDFText_FindClose(FPDF_SCHHANDLE handle);
// Prepare information about weblinks in a page.
// Parameters:
// text_page - Handle to a text page information structure.
// Returned by FPDFText_LoadPage function.
// Returned by FPDFText_LoadPage function.
// Return Value:
// A handle to the page's links information structure.
// A handle to the page's links information structure, or
// NULL if something goes wrong.
// Comments:
// Weblinks are those links implicitly embedded in PDF pages. PDF also
// has a type of
// annotation called "link", FPDFTEXT doesn't deal with that kind of
// link.
// FPDFTEXT weblink feature is useful for automatically detecting links
// in the page
// contents. For example, things like "http://www.foxitsoftware.com"
// will be detected,
// so applications can allow user to click on those characters to
// activate the link,
// even the PDF doesn't come with link annotations.
// has a type of annotation called "link" (FPDFTEXT doesn't deal with
// that kind of link). FPDFTEXT weblink feature is useful for
// automatically detecting links in the page contents. For example,
// things like "https://www.example.com" will be detected, so
// applications can allow user to click on those characters to activate
// the link, even the PDF doesn't come with link annotations.
//
// FPDFLink_CloseWebLinks must be called to release resources.
//
@ -411,16 +591,16 @@ FPDF_EXPORT int FPDF_CALLCONV FPDFLink_CountWebLinks(FPDF_PAGELINK link_page);
// link_page - Handle returned by FPDFLink_LoadWebLinks.
// link_index - Zero-based index for the link.
// buffer - A unicode buffer for the result.
// buflen - Number of characters (not bytes) for the buffer,
// including an additional terminator.
// buflen - Number of 16-bit code units (not bytes) for the
// buffer, including an additional terminator.
// Return Value:
// If |buffer| is NULL or |buflen| is zero, return the number of
// characters (not bytes) needed to buffer the result (an additional
// If |buffer| is NULL or |buflen| is zero, return the number of 16-bit
// code units (not bytes) needed to buffer the result (an additional
// terminator is included in this count).
// Otherwise, copy the result into |buffer|, truncating at |buflen| if
// the result is too large to fit, and return the number of characters
// actually copied into the buffer (the additional terminator is also
// included in this count).
// the result is too large to fit, and return the number of 16-bit code
// units actually copied into the buffer (the additional terminator is
// also included in this count).
// If |link_index| does not correspond to a valid link, then the result
// is an empty string.
//
@ -469,6 +649,26 @@ FPDF_EXPORT FPDF_BOOL FPDF_CALLCONV FPDFLink_GetRect(FPDF_PAGELINK link_page,
double* right,
double* bottom);
// Experimental API.
// Function: FPDFLink_GetTextRange
// Fetch the start char index and char count for a link.
// Parameters:
// link_page - Handle returned by FPDFLink_LoadWebLinks.
// link_index - Zero-based index for the link.
// start_char_index - pointer to int receiving the start char index
// char_count - pointer to int receiving the char count
// Return Value:
// On success, return TRUE and fill in |start_char_index| and
// |char_count|. if |link_page| is invalid or if |link_index| does
// not correspond to a valid link, then return FALSE and the out
// parameters remain unmodified.
//
FPDF_EXPORT FPDF_BOOL FPDF_CALLCONV
FPDFLink_GetTextRange(FPDF_PAGELINK link_page,
int link_index,
int* start_char_index,
int* char_count);
// Function: FPDFLink_CloseWebLinks
// Release resources used by weblink feature.
// Parameters: