diff options
author | dsinclair <dsinclair@chromium.org> | 2016-04-19 10:39:24 -0700 |
---|---|---|
committer | Commit bot <commit-bot@chromium.org> | 2016-04-19 10:39:24 -0700 |
commit | a28ae388f3859c52630deb6ef3d0ea468e5177e3 (patch) | |
tree | 1ab55ded754a5d1fc6ab5702e9d2244e5830ed68 /core/fpdftext/include | |
parent | 11178284eccf22306338cf0d252b8dbb946feb16 (diff) | |
download | pdfium-a28ae388f3859c52630deb6ef3d0ea468e5177e3.tar.xz |
Remove IPDF_TextPage, IPDF_TextPageFind and IPDF_LinkExtract interfaces.
Each was only used by one subclass. Removed and used the concrete classes.
BUG=pdfium:468
Review URL: https://codereview.chromium.org/1897993002
Diffstat (limited to 'core/fpdftext/include')
-rw-r--r-- | core/fpdftext/include/cpdf_linkextract.h | 54 | ||||
-rw-r--r-- | core/fpdftext/include/cpdf_textpage.h | 157 | ||||
-rw-r--r-- | core/fpdftext/include/cpdf_textpagefind.h | 65 | ||||
-rw-r--r-- | core/fpdftext/include/ipdf_linkextract.h | 26 | ||||
-rw-r--r-- | core/fpdftext/include/ipdf_textpage.h | 70 | ||||
-rw-r--r-- | core/fpdftext/include/ipdf_textpagefind.h | 29 |
6 files changed, 276 insertions, 125 deletions
diff --git a/core/fpdftext/include/cpdf_linkextract.h b/core/fpdftext/include/cpdf_linkextract.h new file mode 100644 index 0000000000..263768ee5d --- /dev/null +++ b/core/fpdftext/include/cpdf_linkextract.h @@ -0,0 +1,54 @@ +// Copyright 2014 PDFium Authors. All rights reserved. +// Use of this source code is governed by a BSD-style license that can be +// found in the LICENSE file. + +// Original code copyright 2014 Foxit Software Inc. http://www.foxitsoftware.com + +#ifndef CORE_FPDFTEXT_INCLUDE_CPDF_LINKEXTRACT_H_ +#define CORE_FPDFTEXT_INCLUDE_CPDF_LINKEXTRACT_H_ + +#include "core/fxcrt/include/fx_basic.h" +#include "core/fxcrt/include/fx_coordinates.h" +#include "core/fxcrt/include/fx_string.h" +#include "core/fxcrt/include/fx_system.h" + +class CPDF_TextPage; + +class CPDF_LinkExt { + public: + CPDF_LinkExt() {} + ~CPDF_LinkExt() {} + + int m_Start; + int m_Count; + CFX_WideString m_strUrl; +}; + +class CPDF_LinkExtract { + public: + CPDF_LinkExtract(); + ~CPDF_LinkExtract(); + + FX_BOOL ExtractLinks(const CPDF_TextPage* pTextPage); + int CountLinks() const; + CFX_WideString GetURL(int index) const; + void GetBoundedSegment(int index, int& start, int& count) const; + void GetRects(int index, CFX_RectArray& rects) const; + + FX_BOOL IsExtract() const { return m_bIsParsed; } + + protected: + void ParseLink(); + void DeleteLinkList(); + FX_BOOL CheckWebLink(CFX_WideString& strBeCheck); + bool CheckMailLink(CFX_WideString& str); + void AppendToLinkList(int start, int count, const CFX_WideString& strUrl); + + private: + CFX_ArrayTemplate<CPDF_LinkExt*> m_LinkList; + const CPDF_TextPage* m_pTextPage; + CFX_WideString m_strPageText; + bool m_bIsParsed; +}; + +#endif // CORE_FPDFTEXT_INCLUDE_CPDF_LINKEXTRACT_H_ diff --git a/core/fpdftext/include/cpdf_textpage.h b/core/fpdftext/include/cpdf_textpage.h new file mode 100644 index 0000000000..19e8791b5a --- /dev/null +++ b/core/fpdftext/include/cpdf_textpage.h @@ -0,0 +1,157 @@ +// Copyright 2016 PDFium Authors. All rights reserved. +// Use of this source code is governed by a BSD-style license that can be +// found in the LICENSE file. + +// Original code copyright 2014 Foxit Software Inc. http://www.foxitsoftware.com + +#ifndef CORE_FPDFTEXT_INCLUDE_CPDF_TEXTPAGE_H_ +#define CORE_FPDFTEXT_INCLUDE_CPDF_TEXTPAGE_H_ + +#include <deque> +#include <vector> + +#include "core/fpdfapi/fpdf_page/cpdf_pageobjectlist.h" +#include "core/fxcrt/include/fx_basic.h" +#include "core/fxcrt/include/fx_coordinates.h" +#include "core/fxcrt/include/fx_string.h" + +class CFX_BidiChar; +class CPDF_Font; +class CPDF_FormObject; +class CPDF_Page; +class CPDF_TextObject; + +struct FPDF_CHAR_INFO { + FX_WCHAR m_Unicode; + FX_WCHAR m_Charcode; + int32_t m_Flag; + FX_FLOAT m_FontSize; + FX_FLOAT m_OriginX; + FX_FLOAT m_OriginY; + CFX_FloatRect m_CharBox; + CPDF_TextObject* m_pTextObj; + CFX_Matrix m_Matrix; +}; + +struct FPDF_SEGMENT { + int m_Start; + int m_nCount; +}; + +struct PAGECHAR_INFO { + int m_CharCode; + FX_WCHAR m_Unicode; + FX_FLOAT m_OriginX; + FX_FLOAT m_OriginY; + int32_t m_Flag; + CFX_FloatRect m_CharBox; + CPDF_TextObject* m_pTextObj; + CFX_Matrix m_Matrix; + int m_Index; +}; + +struct PDFTEXT_Obj { + CPDF_TextObject* m_pTextObj; + CFX_Matrix m_formMatrix; +}; + +class CPDF_TextPage { + public: + CPDF_TextPage(const CPDF_Page* pPage, int flags); + ~CPDF_TextPage() {} + + // IPDF_TextPage: + void ParseTextPage(); + bool IsParsed() const { return m_bIsParsed; } + int CharIndexFromTextIndex(int TextIndex) const; + int TextIndexFromCharIndex(int CharIndex) const; + int CountChars() const; + void GetCharInfo(int index, FPDF_CHAR_INFO* info) const; + void GetRectArray(int start, int nCount, CFX_RectArray& rectArray) const; + int GetIndexAtPos(CFX_FloatPoint point, + FX_FLOAT xTolerance, + FX_FLOAT yTolerance) const; + int GetIndexAtPos(FX_FLOAT x, + FX_FLOAT y, + FX_FLOAT xTolerance, + FX_FLOAT yTolerance) const; + CFX_WideString GetTextByRect(const CFX_FloatRect& rect) const; + void GetRectsArrayByRect(const CFX_FloatRect& rect, + CFX_RectArray& resRectArray) const; + CFX_WideString GetPageText(int start = 0, int nCount = -1) const; + int CountRects(int start, int nCount); + void GetRect(int rectIndex, + FX_FLOAT& left, + FX_FLOAT& top, + FX_FLOAT& right, + FX_FLOAT& bottom) const; + FX_BOOL GetBaselineRotate(int rectIndex, int& Rotate); + FX_BOOL GetBaselineRotate(const CFX_FloatRect& rect, int& Rotate); + int CountBoundedSegments(FX_FLOAT left, + FX_FLOAT top, + FX_FLOAT right, + FX_FLOAT bottom, + FX_BOOL bContains = FALSE); + void GetBoundedSegment(int index, int& start, int& count) const; + int GetWordBreak(int index, int direction) const; + + static FX_BOOL IsRectIntersect(const CFX_FloatRect& rect1, + const CFX_FloatRect& rect2); + static FX_BOOL IsLetter(FX_WCHAR unicode); + + private: + FX_BOOL IsHyphen(FX_WCHAR curChar); + bool IsControlChar(const PAGECHAR_INFO& charInfo); + FX_BOOL GetBaselineRotate(int start, int end, int& Rotate); + void ProcessObject(); + void ProcessFormObject(CPDF_FormObject* pFormObj, + const CFX_Matrix& formMatrix); + void ProcessTextObject(PDFTEXT_Obj pObj); + void ProcessTextObject(CPDF_TextObject* pTextObj, + const CFX_Matrix& formMatrix, + const CPDF_PageObjectList* pObjList, + CPDF_PageObjectList::const_iterator ObjPos); + int ProcessInsertObject(const CPDF_TextObject* pObj, + const CFX_Matrix& formMatrix); + FX_BOOL GenerateCharInfo(FX_WCHAR unicode, PAGECHAR_INFO& info); + FX_BOOL IsSameAsPreTextObject(CPDF_TextObject* pTextObj, + const CPDF_PageObjectList* pObjList, + CPDF_PageObjectList::const_iterator ObjPos); + FX_BOOL IsSameTextObject(CPDF_TextObject* pTextObj1, + CPDF_TextObject* pTextObj2); + int GetCharWidth(uint32_t charCode, CPDF_Font* pFont) const; + void CloseTempLine(); + void OnPiece(CFX_BidiChar* pBidi, CFX_WideString& str); + int32_t PreMarkedContent(PDFTEXT_Obj pObj); + void ProcessMarkedContent(PDFTEXT_Obj pObj); + void CheckMarkedContentObject(int32_t& start, int32_t& nCount) const; + void FindPreviousTextObject(void); + void AddCharInfoByLRDirection(FX_WCHAR wChar, PAGECHAR_INFO info); + void AddCharInfoByRLDirection(FX_WCHAR wChar, PAGECHAR_INFO info); + int32_t GetTextObjectWritingMode(const CPDF_TextObject* pTextObj); + int32_t FindTextlineFlowDirection(); + + void SwapTempTextBuf(int32_t iCharListStartAppend, int32_t iBufStartAppend); + FX_BOOL IsRightToLeft(const CPDF_TextObject* pTextObj, + const CPDF_Font* pFont, + int nItems) const; + + const CPDF_Page* const m_pPage; + std::vector<uint16_t> m_CharIndex; + std::deque<PAGECHAR_INFO> m_CharList; + std::deque<PAGECHAR_INFO> m_TempCharList; + CFX_WideTextBuf m_TextBuf; + CFX_WideTextBuf m_TempTextBuf; + const int m_parserflag; + CPDF_TextObject* m_pPreTextObj; + CFX_Matrix m_perMatrix; + bool m_bIsParsed; + CFX_Matrix m_DisplayMatrix; + CFX_ArrayTemplate<FPDF_SEGMENT> m_Segments; + CFX_RectArray m_SelRects; + CFX_ArrayTemplate<PDFTEXT_Obj> m_LineObj; + int32_t m_TextlineDir; + CFX_FloatRect m_CurlineRect; +}; + +#endif // CORE_FPDFTEXT_INCLUDE_CPDF_TEXTPAGE_H_ diff --git a/core/fpdftext/include/cpdf_textpagefind.h b/core/fpdftext/include/cpdf_textpagefind.h new file mode 100644 index 0000000000..ec739e4896 --- /dev/null +++ b/core/fpdftext/include/cpdf_textpagefind.h @@ -0,0 +1,65 @@ +// Copyright 2016 PDFium Authors. All rights reserved. +// Use of this source code is governed by a BSD-style license that can be +// found in the LICENSE file. + +// Original code copyright 2014 Foxit Software Inc. http://www.foxitsoftware.com + +#ifndef CORE_FPDFTEXT_INCLUDE_CPDF_TEXTPAGEFIND_H_ +#define CORE_FPDFTEXT_INCLUDE_CPDF_TEXTPAGEFIND_H_ + +#include <vector> + +#include "core/fxcrt/include/fx_coordinates.h" +#include "core/fxcrt/include/fx_string.h" +#include "core/fxcrt/include/fx_system.h" + +class CPDF_TextPage; + +class CPDF_TextPageFind { + public: + explicit CPDF_TextPageFind(const CPDF_TextPage* pTextPage); + ~CPDF_TextPageFind() {} + + FX_BOOL FindFirst(const CFX_WideString& findwhat, + int flags, + int startPos = 0); + FX_BOOL FindNext(); + FX_BOOL FindPrev(); + void GetRectArray(CFX_RectArray& rects) const; + int GetCurOrder() const; + int GetMatchedCount() const; + + protected: + void ExtractFindWhat(const CFX_WideString& findwhat); + FX_BOOL IsMatchWholeWord(const CFX_WideString& csPageText, + int startPos, + int endPos); + FX_BOOL ExtractSubString(CFX_WideString& rString, + const FX_WCHAR* lpszFullString, + int iSubString, + FX_WCHAR chSep); + CFX_WideString MakeReverse(const CFX_WideString& str); + int ReverseFind(const CFX_WideString& csPageText, + const CFX_WideString& csWord, + int nStartPos, + int& WordLength); + int GetCharIndex(int index) const; + + private: + std::vector<uint16_t> m_CharIndex; + const CPDF_TextPage* m_pTextPage; + CFX_WideString m_strText; + CFX_WideString m_findWhat; + int m_flags; + std::vector<CFX_WideString> m_csFindWhatArray; + int m_findNextStart; + int m_findPreStart; + FX_BOOL m_bMatchCase; + FX_BOOL m_bMatchWholeWord; + int m_resStart; + int m_resEnd; + CFX_RectArray m_resArray; + FX_BOOL m_IsFind; +}; + +#endif // CORE_FPDFTEXT_INCLUDE_CPDF_TEXTPAGEFIND_H_ diff --git a/core/fpdftext/include/ipdf_linkextract.h b/core/fpdftext/include/ipdf_linkextract.h deleted file mode 100644 index c1a5f2f04e..0000000000 --- a/core/fpdftext/include/ipdf_linkextract.h +++ /dev/null @@ -1,26 +0,0 @@ -// Copyright 2016 PDFium Authors. All rights reserved. -// Use of this source code is governed by a BSD-style license that can be -// found in the LICENSE file. - -// Original code copyright 2014 Foxit Software Inc. http://www.foxitsoftware.com - -#ifndef CORE_FPDFTEXT_INCLUDE_IPDF_LINKEXTRACT_H_ -#define CORE_FPDFTEXT_INCLUDE_IPDF_LINKEXTRACT_H_ - -#include "core/fpdftext/include/ipdf_textpage.h" -#include "core/fxcrt/include/fx_coordinates.h" -#include "core/fxcrt/include/fx_system.h" - -class IPDF_LinkExtract { - public: - static IPDF_LinkExtract* CreateLinkExtract(); - virtual ~IPDF_LinkExtract() {} - - virtual FX_BOOL ExtractLinks(const IPDF_TextPage* pTextPage) = 0; - virtual int CountLinks() const = 0; - virtual CFX_WideString GetURL(int index) const = 0; - virtual void GetBoundedSegment(int index, int& start, int& count) const = 0; - virtual void GetRects(int index, CFX_RectArray& rects) const = 0; -}; - -#endif // CORE_FPDFTEXT_INCLUDE_IPDF_LINKEXTRACT_H_ diff --git a/core/fpdftext/include/ipdf_textpage.h b/core/fpdftext/include/ipdf_textpage.h deleted file mode 100644 index 3849cd4004..0000000000 --- a/core/fpdftext/include/ipdf_textpage.h +++ /dev/null @@ -1,70 +0,0 @@ -// Copyright 2016 PDFium Authors. All rights reserved. -// Use of this source code is governed by a BSD-style license that can be -// found in the LICENSE file. - -// Original code copyright 2014 Foxit Software Inc. http://www.foxitsoftware.com - -#ifndef CORE_FPDFTEXT_INCLUDE_IPDF_TEXTPAGE_H_ -#define CORE_FPDFTEXT_INCLUDE_IPDF_TEXTPAGE_H_ - -#include "core/fxcrt/include/fx_coordinates.h" -#include "core/fxcrt/include/fx_system.h" - -class CPDF_TextObject; -class CPDF_Page; - -struct FPDF_CHAR_INFO { - FX_WCHAR m_Unicode; - FX_WCHAR m_Charcode; - int32_t m_Flag; - FX_FLOAT m_FontSize; - FX_FLOAT m_OriginX; - FX_FLOAT m_OriginY; - CFX_FloatRect m_CharBox; - CPDF_TextObject* m_pTextObj; - CFX_Matrix m_Matrix; -}; - -class IPDF_TextPage { - public: - static IPDF_TextPage* CreateTextPage(const CPDF_Page* pPage, int flags = 0); - virtual ~IPDF_TextPage() {} - - virtual void ParseTextPage() = 0; - virtual bool IsParsed() const = 0; - virtual int CharIndexFromTextIndex(int TextIndex) const = 0; - virtual int TextIndexFromCharIndex(int CharIndex) const = 0; - virtual int CountChars() const = 0; - virtual void GetCharInfo(int index, FPDF_CHAR_INFO* info) const = 0; - virtual void GetRectArray(int start, - int nCount, - CFX_RectArray& rectArray) const = 0; - virtual int GetIndexAtPos(CFX_FloatPoint point, - FX_FLOAT xTolerance, - FX_FLOAT yTolerance) const = 0; - virtual int GetIndexAtPos(FX_FLOAT x, - FX_FLOAT y, - FX_FLOAT xTolerance, - FX_FLOAT yTolerance) const = 0; - virtual CFX_WideString GetTextByRect(const CFX_FloatRect& rect) const = 0; - virtual void GetRectsArrayByRect(const CFX_FloatRect& rect, - CFX_RectArray& resRectArray) const = 0; - virtual int CountRects(int start, int nCount) = 0; - virtual void GetRect(int rectIndex, - FX_FLOAT& left, - FX_FLOAT& top, - FX_FLOAT& right, - FX_FLOAT& bottom) const = 0; - virtual FX_BOOL GetBaselineRotate(int rectIndex, int& Rotate) = 0; - virtual FX_BOOL GetBaselineRotate(const CFX_FloatRect& rect, int& Rotate) = 0; - virtual int CountBoundedSegments(FX_FLOAT left, - FX_FLOAT top, - FX_FLOAT right, - FX_FLOAT bottom, - FX_BOOL bContains = FALSE) = 0; - virtual void GetBoundedSegment(int index, int& start, int& count) const = 0; - virtual int GetWordBreak(int index, int direction) const = 0; - virtual CFX_WideString GetPageText(int start = 0, int nCount = -1) const = 0; -}; - -#endif // CORE_FPDFTEXT_INCLUDE_IPDF_TEXTPAGE_H_ diff --git a/core/fpdftext/include/ipdf_textpagefind.h b/core/fpdftext/include/ipdf_textpagefind.h deleted file mode 100644 index b13432b59b..0000000000 --- a/core/fpdftext/include/ipdf_textpagefind.h +++ /dev/null @@ -1,29 +0,0 @@ -// Copyright 2016 PDFium Authors. All rights reserved. -// Use of this source code is governed by a BSD-style license that can be -// found in the LICENSE file. - -// Original code copyright 2014 Foxit Software Inc. http://www.foxitsoftware.com - -#ifndef CORE_FPDFTEXT_INCLUDE_IPDF_TEXTPAGEFIND_H_ -#define CORE_FPDFTEXT_INCLUDE_IPDF_TEXTPAGEFIND_H_ - -#include "core/fpdftext/include/ipdf_textpage.h" -#include "core/fxcrt/include/fx_coordinates.h" -#include "core/fxcrt/include/fx_string.h" - -class IPDF_TextPageFind { - public: - static IPDF_TextPageFind* CreatePageFind(const IPDF_TextPage* pTextPage); - virtual ~IPDF_TextPageFind() {} - - virtual FX_BOOL FindFirst(const CFX_WideString& findwhat, - int flags, - int startPos = 0) = 0; - virtual FX_BOOL FindNext() = 0; - virtual FX_BOOL FindPrev() = 0; - virtual void GetRectArray(CFX_RectArray& rects) const = 0; - virtual int GetCurOrder() const = 0; - virtual int GetMatchedCount() const = 0; -}; - -#endif // CORE_FPDFTEXT_INCLUDE_IPDF_TEXTPAGEFIND_H_ |