diff options
author | npm <npm@chromium.org> | 2016-11-07 08:42:11 -0800 |
---|---|---|
committer | Commit bot <commit-bot@chromium.org> | 2016-11-07 08:42:11 -0800 |
commit | 014b012278b7438ef8d4b66730b8598c7eb4623a (patch) | |
tree | 75ea0ea37d0b239412133290d7b24cc975bfcc66 /core/fpdfapi/page/cpdf_contentparser.cpp | |
parent | 240dec52b2e6502e7deb27a3535af3b1a3e23428 (diff) | |
download | pdfium-014b012278b7438ef8d4b66730b8598c7eb4623a.tar.xz |
Clean up fpdf_page_parsers
- The code in fpdf_page_parser is only called by CPDF_StreamContentParser, so moved there.
- Split fpdf_page_parser_old into its two classes
- Renamed the corresponding unittests accordingly.
- Moved PDF_ReplaceAbbr to namespace
- Fixed few nits
- Added TODO because CPDF_StreamParser has a lot of code similar to CPDF_SyntaxParser
Review-Url: https://codereview.chromium.org/2474303003
Diffstat (limited to 'core/fpdfapi/page/cpdf_contentparser.cpp')
-rw-r--r-- | core/fpdfapi/page/cpdf_contentparser.cpp | 215 |
1 files changed, 215 insertions, 0 deletions
diff --git a/core/fpdfapi/page/cpdf_contentparser.cpp b/core/fpdfapi/page/cpdf_contentparser.cpp new file mode 100644 index 0000000000..f581047835 --- /dev/null +++ b/core/fpdfapi/page/cpdf_contentparser.cpp @@ -0,0 +1,215 @@ +// 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 + +#include "core/fpdfapi/page/pageint.h" + +#include "core/fpdfapi/font/cpdf_type3char.h" +#include "core/fpdfapi/page/cpdf_allstates.h" +#include "core/fpdfapi/page/cpdf_form.h" +#include "core/fpdfapi/page/cpdf_page.h" +#include "core/fpdfapi/page/cpdf_pageobject.h" +#include "core/fpdfapi/page/cpdf_path.h" +#include "core/fpdfapi/parser/cpdf_array.h" +#include "core/fpdfapi/parser/cpdf_dictionary.h" +#include "core/fpdfapi/parser/cpdf_stream.h" +#include "core/fpdfapi/parser/cpdf_stream_acc.h" +#include "core/fxcrt/fx_safe_types.h" + +CPDF_ContentParser::CPDF_ContentParser() + : m_Status(Ready), + m_InternalStage(STAGE_GETCONTENT), + m_pObjectHolder(nullptr), + m_bForm(false), + m_pType3Char(nullptr), + m_pData(nullptr), + m_Size(0), + m_CurrentOffset(0) {} + +CPDF_ContentParser::~CPDF_ContentParser() { + if (!m_pSingleStream) + FX_Free(m_pData); +} + +void CPDF_ContentParser::Start(CPDF_Page* pPage) { + if (m_Status != Ready || !pPage || !pPage->m_pDocument || + !pPage->m_pFormDict) { + m_Status = Done; + return; + } + m_pObjectHolder = pPage; + m_bForm = false; + m_Status = ToBeContinued; + m_InternalStage = STAGE_GETCONTENT; + m_CurrentOffset = 0; + + CPDF_Object* pContent = pPage->m_pFormDict->GetDirectObjectFor("Contents"); + if (!pContent) { + m_Status = Done; + return; + } + if (CPDF_Stream* pStream = pContent->AsStream()) { + m_nStreams = 0; + m_pSingleStream.reset(new CPDF_StreamAcc); + m_pSingleStream->LoadAllData(pStream, false); + } else if (CPDF_Array* pArray = pContent->AsArray()) { + m_nStreams = pArray->GetCount(); + if (m_nStreams) + m_StreamArray.resize(m_nStreams); + else + m_Status = Done; + } else { + m_Status = Done; + } +} + +void CPDF_ContentParser::Start(CPDF_Form* pForm, + CPDF_AllStates* pGraphicStates, + const CFX_Matrix* pParentMatrix, + CPDF_Type3Char* pType3Char, + int level) { + m_pType3Char = pType3Char; + m_pObjectHolder = pForm; + m_bForm = true; + CFX_Matrix form_matrix = pForm->m_pFormDict->GetMatrixFor("Matrix"); + if (pGraphicStates) + form_matrix.Concat(pGraphicStates->m_CTM); + CPDF_Array* pBBox = pForm->m_pFormDict->GetArrayFor("BBox"); + CFX_FloatRect form_bbox; + CPDF_Path ClipPath; + if (pBBox) { + form_bbox = pBBox->GetRect(); + ClipPath.Emplace(); + ClipPath.AppendRect(form_bbox.left, form_bbox.bottom, form_bbox.right, + form_bbox.top); + ClipPath.Transform(&form_matrix); + if (pParentMatrix) + ClipPath.Transform(pParentMatrix); + form_bbox.Transform(&form_matrix); + if (pParentMatrix) + form_bbox.Transform(pParentMatrix); + } + CPDF_Dictionary* pResources = pForm->m_pFormDict->GetDictFor("Resources"); + m_pParser.reset(new CPDF_StreamContentParser( + pForm->m_pDocument, pForm->m_pPageResources, pForm->m_pResources, + pParentMatrix, pForm, pResources, &form_bbox, pGraphicStates, level)); + m_pParser->GetCurStates()->m_CTM = form_matrix; + m_pParser->GetCurStates()->m_ParentMatrix = form_matrix; + if (ClipPath) { + m_pParser->GetCurStates()->m_ClipPath.AppendPath(ClipPath, FXFILL_WINDING, + true); + } + if (pForm->m_Transparency & PDFTRANS_GROUP) { + CPDF_GeneralState* pState = &m_pParser->GetCurStates()->m_GeneralState; + pState->SetBlendType(FXDIB_BLEND_NORMAL); + pState->SetStrokeAlpha(1.0f); + pState->SetFillAlpha(1.0f); + pState->SetSoftMask(nullptr); + } + m_nStreams = 0; + m_pSingleStream.reset(new CPDF_StreamAcc); + m_pSingleStream->LoadAllData(pForm->m_pFormStream, false); + m_pData = (uint8_t*)m_pSingleStream->GetData(); + m_Size = m_pSingleStream->GetSize(); + m_Status = ToBeContinued; + m_InternalStage = STAGE_PARSE; + m_CurrentOffset = 0; +} + +void CPDF_ContentParser::Continue(IFX_Pause* pPause) { + int steps = 0; + while (m_Status == ToBeContinued) { + if (m_InternalStage == STAGE_GETCONTENT) { + if (m_CurrentOffset == m_nStreams) { + if (!m_StreamArray.empty()) { + FX_SAFE_UINT32 safeSize = 0; + for (const auto& stream : m_StreamArray) { + safeSize += stream->GetSize(); + safeSize += 1; + } + if (!safeSize.IsValid()) { + m_Status = Done; + return; + } + m_Size = safeSize.ValueOrDie(); + m_pData = FX_Alloc(uint8_t, m_Size); + uint32_t pos = 0; + for (const auto& stream : m_StreamArray) { + FXSYS_memcpy(m_pData + pos, stream->GetData(), stream->GetSize()); + pos += stream->GetSize(); + m_pData[pos++] = ' '; + } + m_StreamArray.clear(); + } else { + m_pData = (uint8_t*)m_pSingleStream->GetData(); + m_Size = m_pSingleStream->GetSize(); + } + m_InternalStage = STAGE_PARSE; + m_CurrentOffset = 0; + } else { + CPDF_Array* pContent = + m_pObjectHolder->m_pFormDict->GetArrayFor("Contents"); + m_StreamArray[m_CurrentOffset].reset(new CPDF_StreamAcc); + CPDF_Stream* pStreamObj = ToStream( + pContent ? pContent->GetDirectObjectAt(m_CurrentOffset) : nullptr); + m_StreamArray[m_CurrentOffset]->LoadAllData(pStreamObj, false); + m_CurrentOffset++; + } + } + if (m_InternalStage == STAGE_PARSE) { + if (!m_pParser) { + m_pParser.reset(new CPDF_StreamContentParser( + m_pObjectHolder->m_pDocument, m_pObjectHolder->m_pPageResources, + nullptr, nullptr, m_pObjectHolder, m_pObjectHolder->m_pResources, + &m_pObjectHolder->m_BBox, nullptr, 0)); + m_pParser->GetCurStates()->m_ColorState.SetDefault(); + } + if (m_CurrentOffset >= m_Size) { + m_InternalStage = STAGE_CHECKCLIP; + } else { + m_CurrentOffset += + m_pParser->Parse(m_pData + m_CurrentOffset, + m_Size - m_CurrentOffset, PARSE_STEP_LIMIT); + } + } + if (m_InternalStage == STAGE_CHECKCLIP) { + if (m_pType3Char) { + m_pType3Char->m_bColored = m_pParser->IsColored(); + m_pType3Char->m_Width = + FXSYS_round(m_pParser->GetType3Data()[0] * 1000); + m_pType3Char->m_BBox.left = + FXSYS_round(m_pParser->GetType3Data()[2] * 1000); + m_pType3Char->m_BBox.bottom = + FXSYS_round(m_pParser->GetType3Data()[3] * 1000); + m_pType3Char->m_BBox.right = + FXSYS_round(m_pParser->GetType3Data()[4] * 1000); + m_pType3Char->m_BBox.top = + FXSYS_round(m_pParser->GetType3Data()[5] * 1000); + } + for (auto& pObj : *m_pObjectHolder->GetPageObjectList()) { + if (!pObj->m_ClipPath) + continue; + if (pObj->m_ClipPath.GetPathCount() != 1) + continue; + if (pObj->m_ClipPath.GetTextCount()) + continue; + CPDF_Path ClipPath = pObj->m_ClipPath.GetPath(0); + if (!ClipPath.IsRect() || pObj->IsShading()) + continue; + CFX_FloatRect old_rect(ClipPath.GetPointX(0), ClipPath.GetPointY(0), + ClipPath.GetPointX(2), ClipPath.GetPointY(2)); + CFX_FloatRect obj_rect(pObj->m_Left, pObj->m_Bottom, pObj->m_Right, + pObj->m_Top); + if (old_rect.Contains(obj_rect)) + pObj->m_ClipPath.SetNull(); + } + m_Status = Done; + return; + } + steps++; + if (pPause && pPause->NeedToPauseNow()) + break; + } +} |