59 typedef enum _TextCharFlag {
276 typedef enum _TextParseFlags {
290 typedef enum _TextOrderFlag {
524 typedef enum _SearchFlags {
915 #endif // FS_SEARCH_H_
TextParseFlags
Enumeration for parsing flags used for text page.
Definition: fs_search.h:276
If set, match the case of keyword when searching.
Definition: fs_search.h:528
bool IsEmpty() const
Check whether current object is empty or not.
Definition: fs_search.h:843
If this is set, that means to get text content of a PDF page by the stream order.
Definition: fs_search.h:292
float origin_x
The x-coordinate of the origin position.
Definition: fs_search.h:231
RectF char_box
The glyph bounding box in page space.
Definition: fs_search.h:241
void * FS_HANDLE
Handle type.
Definition: fs_basictypes.h:216
Parse the text content of a PDF page with outputting the hyphen on a line feed.
Definition: fs_search.h:280
RectFArray GetTextRectArrayByRect(const RectF &rect)
Get the array of all text rectangles within the specified rectangle region.
Definition: fs_annot.h:754
common::Font font
A font for character.
Definition: fs_search.h:211
int GetCharCount() const
Get the count of all the characters.
bool IsEmpty() const
Check whether current object is empty or not.
bool SetEndPage(int page_index)
Set ending page index.
int GetStartCharIndex()
Get the index of start character of current hyper-link URI, based on PDF page.
CFX_Object Object
Object type.
Definition: fs_basictypes.h:219
TextCharFlag flag
Flags to indicate which properties of textpage character flag are meaningful.
Definition: fs_search.h:219
int GetMatchStartCharIndex() const
Get the index of the first character of current match pattern, based on current match page.
bool operator !=(const TextPageCharInfo &char_info) const
Not equal operator.
Definition: fs_search.h:170
Matrix matrix
The matrix of the character.
Definition: fs_search.h:251
TextPage & operator=(const TextPage &other)
Assign operator.
virtual bool NeedToCancelNow()=0
A callback function used to check whether to cancel the searching process or not.
bool operator==(const TextLink &other) const
Equal operator.
float origin_y
The y-coordinate of the origin position.
Definition: fs_search.h:236
RectF GetTextRect(int rect_index) const
Get the text rectangle by the index.
If this is set, that means to get text content of a PDF page by the display order.
Definition: fs_search.h:294
Definition: fs_search.h:269
common::Range GetWordAtPos(float x, float y, float tolerance) const
Get the character range of a word at or around a specified position on the page, in PDF coordinate sy...
Character flag: Hyphen.
Definition: fs_search.h:69
Header file for common definitions and classes.
RectFArray GetMatchRects() const
Get the rectangles of current match pattern.
RectFArray GetRects()
Get the text rectangles of current text link object.
Character flag: Generated.
Definition: fs_search.h:65
~TextPageCharInfo()
Destructor.
Definition: fs_search.h:110
RectF char_outbox
The typographic(display and printing) bounding box in page space.
Definition: fs_search.h:246
bool operator !=(const TextSearch &other) const
Not equal operator.
PageTextLinks & operator=(const PageTextLinks &other)
Assign operator.
common::Rotation GetBaselineRotation(int rect_index)
Get the text trend (as rotation) of a specified rectangle.
common::Range GetCharRange(const RectF &rect)
Get the character index range of all text rectangles within the specified rectangle region.
TextLink & operator=(const TextLink &other)
Assign operator.
int GetMatchEndCharIndex() const
Get the index of the last character of current match pattern, based on current match page.
bool operator==(const TextSearch &other) const
Equal operator.
Definition: fs_search.h:52
Parse the text content of a PDF page by the stream order.
Definition: fs_search.h:282
bool IsEmpty() const
Check whether current object is empty or not.
WString GetText(TextOrderFlag flag) const
Get the page text.
bool FindPrev()
Search for previous matched pattern.
TextPageCharInfo(const TextPageCharInfo &char_info)
Constructor, with another character information object.
Definition: fs_search.h:117
float font_size
Font size for character.
Definition: fs_search.h:226
Header file for XFA related definitions and functions.
TextPageCharInfo & operator=(const TextPageCharInfo &char_info)
Assign operator.
Definition: fs_search.h:135
Character flag: UnUnicode.
Definition: fs_search.h:67
WString GetChars(int start=0, int count=-1) const
Get all the characters within a range specified by a start index and count.
bool SetPattern(const wchar_t *key_words)
Set keywords to search.
int GetMatchPageIndex() const
Get the page index, to which current match belongs.
TextSearch(const PDFDoc &document, SearchCancelCallback *cancel=0)
Constructor, for a PDF document.
WString GetURI()
Get URI string.
bool SetStartPage(int page_index)
Set starting page index.
int GetIndexAtPos(float x, float y, float tolerance) const
Get the character index at or around a specified position on the page, in PDF coordinate system.
Rotation
Enumeration for rotation.
Definition: fs_common.h:344
TextLink(const TextLink &other)
Constructor, with another text link object.
Character flag: Normal.
Definition: fs_search.h:63
If set, match the whole word of keyword when searching.
Definition: fs_search.h:530
int GetTextLinkCount()
Get the count of the URL formatted texts, in related PDF page.
If set, match the key word consecutively when searching. For example, "CC" will be matched twice in "...
Definition: fs_search.h:532
TextCharFlag
Enumeration for PDF textpage character flag.
Definition: fs_search.h:59
Header file for PDF page related definitions and classes.
int GetEndCharIndex()
Get the index of last character of current hyper-link URI, based on PDF page.
Foxit namespace.
Definition: fs_compare.h:27
Parse the text content of a PDF page by normalizing characters based on their positions in the PDF pa...
Definition: fs_search.h:278
TextPage(const PDFPage &page, int flags=foxit::pdf::TextPage::e_ParseTextNormal)
Constructor, from a parsed PDF page.
TextSearch & operator=(const TextSearch &other)
Assign operator.
WString GetTextInRect(const RectF &rect) const
Get the text within a rectangle, in PDF coordinate system.
TextPageCharInfo(const common::Font &font, TextCharFlag flag, float font_size, float origin_x, float origin_y, const RectF &char_box, const RectF &char_outbox, const Matrix &matrix)
Constructor, with parameters.
Definition: fs_search.h:90
bool FindNext()
Search for next matched pattern.
TextPageCharInfo()
Constructor.
Definition: fs_search.h:103
bool operator==(const PageTextLinks &other) const
Equal operator.
bool IsEmpty() const
Check whether current object is empty or not.
#define NULL
The null-pointer value.
Definition: fx_system.h:767
bool operator !=(const TextLink &other) const
Not equal operator.
No special searching options.
Definition: fs_search.h:526
Definition: fx_coordinates.h:771
void Set(const common::Font &font, TextCharFlag flag, float font_size, float origin_x, float origin_y, const RectF &char_box, const RectF &char_outbox, const Matrix &matrix)
Set value.
Definition: fs_search.h:196
SearchFlags
Enumeration for searching flags.
Definition: fs_search.h:524
Definition: fs_search.h:517
Definition: fs_pdfdoc.h:389
Definition: fs_pdfpage.h:342
~PageTextLinks()
Destructor.
Definition: fs_search.h:39
Character flag: Unknown.
Definition: fs_search.h:61
Character flag: ComboWord.
Definition: fs_search.h:71
bool SetSearchFlags(uint32 search_flags)
Set search flags.
Definition: fs_common.h:1418
bool operator !=(const TextPage &other) const
Not equal operator.
Definition: fx_coordinates.h:1076
Header file for annotation related definitions and classes.
bool operator !=(const PageTextLinks &other) const
Not equal operator.
bool operator==(const TextPageCharInfo &char_info) const
Equal operator.
Definition: fs_search.h:154
WIDE STRING CLASS.
Definition: fx_string.h:1452
WString GetMatchSentence()
Get the sentence that contains current match pattern.
Definition: fs_common.h:1263
WString GetTextUnderAnnot(annots::Annot &annot) const
Get the page text which intersect with a specified an annotation.
Definition: fs_search.h:759
int GetTextRectCount(int start=0, int count=-1)
Count the text rectangles within a range specified by a start index and count.
FX_UINT32 uint32
32-bit unsigned integer.
Definition: fs_basictypes.h:198
PageTextLinks(const TextPage &page)
Constructor, from a parsed PDF page.
int GetMatchSentenceStartIndex()
Get the index of the first character of current match pattern, based on the match sentence.
Definition: fs_basictypes.h:399
bool operator==(const TextPage &other) const
Equal operator.
TextOrderFlag
Enumeration for text order flag which is used when getting text content of a PDF page.
Definition: fs_search.h:290
TextLink GetTextLink(int index)
Get a text link object by index.
TextPageCharInfo GetCharInfo(int char_index)
Get character information of a specific character.