diff options
author | Tom Sepez <tsepez@chromium.org> | 2016-02-11 09:06:11 -0800 |
---|---|---|
committer | Tom Sepez <tsepez@chromium.org> | 2016-02-11 09:06:11 -0800 |
commit | 6b90e983a9e3e7aee0c637a7b0c3c51f0dfc1faf (patch) | |
tree | 4a7ee0b7d6f381b7e3b4270bf74746db45715a76 /core/src/fpdftext/fpdf_text_search.cpp | |
parent | e238549d212e97fe01dba3740949a98172c21454 (diff) | |
download | pdfium-6b90e983a9e3e7aee0c637a7b0c3c51f0dfc1faf.tar.xz |
Remove unused NormalizeString()
- NormalizeString() has 1 caller:
- CTextBaseLine::WriteOutput(), which has only 1 caller:
- CTextPage::WriteOutput(), which has only 1 caller:
- PDF_GetPageText_Unicode(), which has only 1 caller:
- PDF_GetPageText(), which has no callers.
Removing this also makes CheckRotate(), NormalizeCompositeChar(),
and CTextPage unused.
Removing those makes CTextBaseline() unused.
Removing that makes txtproc.h unused.
PDF_GetTextStream_Unicode also unused.
... and so on until entire files can be removed.
R=thestig@chromium.org
Review URL: https://codereview.chromium.org/1689843002 .
Diffstat (limited to 'core/src/fpdftext/fpdf_text_search.cpp')
-rw-r--r-- | core/src/fpdftext/fpdf_text_search.cpp | 292 |
1 files changed, 0 insertions, 292 deletions
diff --git a/core/src/fpdftext/fpdf_text_search.cpp b/core/src/fpdftext/fpdf_text_search.cpp deleted file mode 100644 index 5bbfbd9198..0000000000 --- a/core/src/fpdftext/fpdf_text_search.cpp +++ /dev/null @@ -1,292 +0,0 @@ -// 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 - -#include "core/include/fpdfapi/fpdf_page.h" -#include "core/include/fpdfapi/fpdf_pageobj.h" -#include "core/src/fpdftext/text_int.h" - -class CPDF_TextStream { - public: - CPDF_TextStream(CFX_WideTextBuf& buffer, FX_BOOL bUseLF) - : m_Buffer(buffer), m_bUseLF(bUseLF), m_pLastObj(nullptr) {} - ~CPDF_TextStream() {} - FX_BOOL ProcessObject(const CPDF_TextObject* pObj, FX_BOOL bFirstLine); - - CFX_WideTextBuf& m_Buffer; - FX_BOOL m_bUseLF; - const CPDF_TextObject* m_pLastObj; -}; -FX_BOOL FPDFText_IsSameTextObject(const CPDF_TextObject* pTextObj1, - const CPDF_TextObject* pTextObj2) { - if (!pTextObj1 || !pTextObj2) { - return FALSE; - } - CFX_FloatRect rcPreObj(pTextObj2->m_Left, pTextObj2->m_Bottom, - pTextObj2->m_Right, pTextObj2->m_Top); - CFX_FloatRect rcCurObj(pTextObj1->m_Left, pTextObj1->m_Bottom, - pTextObj1->m_Right, pTextObj1->m_Top); - if (rcPreObj.IsEmpty() && rcCurObj.IsEmpty()) { - return TRUE; - } - if (!rcPreObj.IsEmpty() || !rcCurObj.IsEmpty()) { - rcPreObj.Intersect(rcCurObj); - if (rcPreObj.IsEmpty()) { - return FALSE; - } - if (FXSYS_fabs(rcPreObj.Width() - rcCurObj.Width()) > - rcCurObj.Width() / 2) { - return FALSE; - } - if (pTextObj2->GetFontSize() != pTextObj1->GetFontSize()) { - return FALSE; - } - } - int nPreCount = pTextObj2->CountItems(); - int nCurCount = pTextObj1->CountItems(); - if (nPreCount != nCurCount) { - return FALSE; - } - for (int i = 0; i < nPreCount; i++) { - CPDF_TextObjectItem itemPer, itemCur; - pTextObj2->GetItemInfo(i, &itemPer); - pTextObj1->GetItemInfo(i, &itemCur); - if (itemCur.m_CharCode != itemPer.m_CharCode) { - return FALSE; - } - } - return TRUE; -} -int GetCharWidth(FX_DWORD charCode, CPDF_Font* pFont) { - if (charCode == -1) { - return 0; - } - int w = pFont->GetCharWidthF(charCode); - if (w == 0) { - CFX_ByteString str; - pFont->AppendChar(str, charCode); - w = pFont->GetStringWidth(str, 1); - if (w == 0) { - FX_RECT BBox; - pFont->GetCharBBox(charCode, BBox); - w = BBox.right - BBox.left; - } - } - return w; -} -int FPDFText_ProcessInterObj(const CPDF_TextObject* pPrevObj, - const CPDF_TextObject* pObj) { - if (FPDFText_IsSameTextObject(pPrevObj, pObj)) { - return -1; - } - CPDF_TextObjectItem item; - int nItem = pPrevObj->CountItems(); - pPrevObj->GetItemInfo(nItem - 1, &item); - FX_WCHAR preChar = 0, curChar = 0; - CFX_WideString wstr = - pPrevObj->GetFont()->UnicodeFromCharCode(item.m_CharCode); - if (wstr.GetLength()) { - preChar = wstr.GetAt(0); - } - FX_FLOAT last_pos = item.m_OriginX; - int nLastWidth = GetCharWidth(item.m_CharCode, pPrevObj->GetFont()); - FX_FLOAT last_width = nLastWidth * pPrevObj->GetFontSize() / 1000; - last_width = FXSYS_fabs(last_width); - pObj->GetItemInfo(0, &item); - wstr = pObj->GetFont()->UnicodeFromCharCode(item.m_CharCode); - if (wstr.GetLength()) { - curChar = wstr.GetAt(0); - } - int nThisWidth = GetCharWidth(item.m_CharCode, pObj->GetFont()); - FX_FLOAT this_width = nThisWidth * pObj->GetFontSize() / 1000; - this_width = FXSYS_fabs(this_width); - FX_FLOAT threshold = - last_width > this_width ? last_width / 4 : this_width / 4; - CFX_Matrix prev_matrix, prev_reverse; - pPrevObj->GetTextMatrix(&prev_matrix); - prev_reverse.SetReverse(prev_matrix); - FX_FLOAT x = pObj->GetPosX(), y = pObj->GetPosY(); - prev_reverse.Transform(x, y); - if (FXSYS_fabs(y) > threshold * 2) { - return 2; - } - threshold = (FX_FLOAT)(nLastWidth > nThisWidth ? nLastWidth : nThisWidth); - threshold = threshold > 400 - ? (threshold < 700 ? threshold / 4 : threshold / 5) - : (threshold / 2); - threshold *= nLastWidth > nThisWidth ? FXSYS_fabs(pPrevObj->GetFontSize()) - : FXSYS_fabs(pObj->GetFontSize()); - threshold /= 1000; - if (FXSYS_fabs(last_pos + last_width - x) > threshold && curChar != L' ' && - preChar != L' ') - if (curChar != L' ' && preChar != L' ') { - if ((x - last_pos - last_width) > threshold || - (last_pos - x - last_width) > threshold) { - return 1; - } - if (x < 0 && (last_pos - x - last_width) > threshold) { - return 1; - } - if ((x - last_pos - last_width) > this_width || - (x - last_pos - this_width) > last_width) { - return 1; - } - } - if (last_pos + last_width > x + this_width && curChar == L' ') { - return 3; - } - return 0; -} -FX_BOOL CPDF_TextStream::ProcessObject(const CPDF_TextObject* pObj, - FX_BOOL bFirstLine) { - CPDF_Font* pFont = pObj->GetFont(); - CFX_Matrix matrix; - pObj->GetTextMatrix(&matrix); - int item_index = 0; - if (m_pLastObj) { - int result = FPDFText_ProcessInterObj(m_pLastObj, pObj); - if (result == 2) { - int len = m_Buffer.GetLength(); - if (len && m_bUseLF && m_Buffer.GetBuffer()[len - 1] == L'-') { - m_Buffer.Delete(len - 1, 1); - } else { - if (bFirstLine) { - return TRUE; - } - if (m_bUseLF) { - m_Buffer.AppendChar(L'\r'); - m_Buffer.AppendChar(L'\n'); - } else { - m_Buffer.AppendChar(' '); - } - } - } else if (result == 1) { - m_Buffer.AppendChar(L' '); - } else if (result == -1) { - m_pLastObj = pObj; - return FALSE; - } else if (result == 3) { - item_index = 1; - } - } - m_pLastObj = pObj; - int nItems = pObj->CountItems(); - FX_FLOAT Ignorekerning = 0; - for (int i = 1; i < nItems - 1; i += 2) { - CPDF_TextObjectItem item; - pObj->GetItemInfo(i, &item); - if (item.m_CharCode == (FX_DWORD)-1) { - if (i == 1) { - Ignorekerning = item.m_OriginX; - } else if (Ignorekerning > item.m_OriginX) { - Ignorekerning = item.m_OriginX; - } - } else { - Ignorekerning = 0; - break; - } - } - FX_FLOAT spacing = 0; - for (; item_index < nItems; item_index++) { - CPDF_TextObjectItem item; - pObj->GetItemInfo(item_index, &item); - if (item.m_CharCode == (FX_DWORD)-1) { - CFX_WideString wstr = m_Buffer.GetWideString(); - if (wstr.IsEmpty() || wstr.GetAt(wstr.GetLength() - 1) == L' ') { - continue; - } - FX_FLOAT fontsize_h = pObj->m_TextState.GetFontSizeH(); - spacing = -fontsize_h * (item.m_OriginX - Ignorekerning) / 1000; - continue; - } - FX_FLOAT charSpace = pObj->m_TextState.GetObject()->m_CharSpace; - if (nItems > 3 && !spacing) { - charSpace = 0; - } - if ((spacing || charSpace) && item_index > 0) { - int last_width = 0; - FX_FLOAT fontsize_h = pObj->m_TextState.GetFontSizeH(); - FX_DWORD space_charcode = pFont->CharCodeFromUnicode(' '); - FX_FLOAT threshold = 0; - if (space_charcode != -1) { - threshold = fontsize_h * pFont->GetCharWidthF(space_charcode) / 1000; - } - if (threshold > fontsize_h / 3) { - threshold = 0; - } else { - threshold /= 2; - } - if (threshold == 0) { - threshold = fontsize_h; - int this_width = FXSYS_abs(GetCharWidth(item.m_CharCode, pFont)); - threshold = this_width > last_width ? (FX_FLOAT)this_width - : (FX_FLOAT)last_width; - int nDivide = 6; - if (threshold < 300) { - nDivide = 2; - } else if (threshold < 500) { - nDivide = 4; - } else if (threshold < 700) { - nDivide = 5; - } - threshold = threshold / nDivide; - threshold = fontsize_h * threshold / 1000; - } - if (charSpace > 0.001) { - spacing += matrix.TransformDistance(charSpace); - } else if (charSpace < -0.001) { - spacing -= matrix.TransformDistance(FXSYS_fabs(charSpace)); - } - if (threshold && (spacing && spacing >= threshold)) { - m_Buffer.AppendChar(L' '); - } - if (item.m_CharCode == (FX_DWORD)-1) { - continue; - } - spacing = 0; - } - CFX_WideString unicode_str = pFont->UnicodeFromCharCode(item.m_CharCode); - if (unicode_str.IsEmpty()) { - m_Buffer.AppendChar((FX_WCHAR)item.m_CharCode); - } else { - m_Buffer << unicode_str; - } - } - return FALSE; -} -void GetTextStream_Unicode(CFX_WideTextBuf& buffer, - CPDF_PageObjectList* pPage, - FX_BOOL bUseLF) { - CPDF_TextStream textstream(buffer, bUseLF); - FX_POSITION pos = pPage->GetFirstObjectPosition(); - while (pos) { - CPDF_PageObject* pObject = pPage->GetNextObject(pos); - if (pObject && pObject->m_Type == CPDF_PageObject::TEXT) - textstream.ProcessObject((CPDF_TextObject*)pObject, FALSE); - } -} -CFX_WideString PDF_GetFirstTextLine_Unicode(CPDF_Document* pDoc, - CPDF_Dictionary* pPage) { - CFX_WideTextBuf buffer; - buffer.EstimateSize(0, 1024); - CPDF_Page page; - page.Load(pDoc, pPage); - CPDF_ParseOptions options; - options.m_bTextOnly = TRUE; - options.m_bSeparateForm = FALSE; - page.ParseContent(&options); - CPDF_TextStream textstream(buffer, FALSE); - FX_POSITION pos = page.GetFirstObjectPosition(); - while (pos) { - CPDF_PageObject* pObject = page.GetNextObject(pos); - if (pObject->m_Type != CPDF_PageObject::TEXT) { - continue; - } - if (textstream.ProcessObject((CPDF_TextObject*)pObject, TRUE)) { - break; - } - } - return buffer.GetWideString(); -} |