Handle web links across lineschromium/3045

When a web link has a hyphen at the end of line, we consider it to
be continued to the next line. For example, "http://www.abc.com/my-\r\ntest"
should be extracted as "http://www.abc.com/my-test".

BUG=pdfium:650

Change-Id: I64a93d9c66faf2be0abdaf8cfe8ee496c435d0ca
Reviewed-on: https://pdfium-review.googlesource.com/3092
Commit-Queue: Wei Li <weili@chromium.org>
Reviewed-by: Lei Zhang <thestig@chromium.org>

2 files changed, 28 insertions, 5 deletions

diff --git a/core/fpdftext/cpdf_linkextract.cpp b/core/fpdftext/cpdf_linkextract.cpp
index 686b6a23b8..47d0754bd2 100644
--- a/core/fpdftext/cpdf_linkextract.cpp
+++ b/core/fpdftext/cpdf_linkextract.cpp
@@ -31,18 +31,36 @@ void CPDF_LinkExtract::ExtractLinks() {
 }
 
 void CPDF_LinkExtract::ParseLink() {
-  int start = 0, pos = 0;
-  int TotalChar = m_pTextPage->CountChars();
-  while (pos < TotalChar) {
+  int start = 0;
+  int pos = 0;
+  int nTotalChar = m_pTextPage->CountChars();
+  bool bAfterHyphen = false;
+  bool bLineBreak = false;
+  while (pos < nTotalChar) {
     FPDF_CHAR_INFO pageChar;
     m_pTextPage->GetCharInfo(pos, &pageChar);
     if (pageChar.m_Flag == FPDFTEXT_CHAR_GENERATED ||
-        pageChar.m_Unicode == 0x20 || pos == TotalChar - 1) {
+        pageChar.m_Unicode == TEXT_SPACE_CHAR || pos == nTotalChar - 1) {
       int nCount = pos - start;
-      if (pos == TotalChar - 1)
+      if (pos == nTotalChar - 1) {
         nCount++;
+      } else if (bAfterHyphen && (pageChar.m_Unicode == TEXT_LINEFEED_CHAR ||
+                                  pageChar.m_Unicode == TEXT_RETURN_CHAR)) {
+        // Handle text breaks with a hyphen to the next line.
+        bLineBreak = true;
+        pos++;
+        continue;
+      }
       CFX_WideString strBeCheck;
       strBeCheck = m_pTextPage->GetPageText(start, nCount);
+      if (bLineBreak) {
+        strBeCheck.Remove(TEXT_LINEFEED_CHAR);
+        strBeCheck.Remove(TEXT_RETURN_CHAR);
+        bLineBreak = false;
+      }
+      // Replace the generated code with the hyphen char.
+      strBeCheck.Replace(L"\xfffe", TEXT_HYPHEN);
+
       if (strBeCheck.GetLength() > 5) {
         while (strBeCheck.GetLength() > 0) {
           wchar_t ch = strBeCheck.GetAt(strBeCheck.GetLength() - 1);
@@ -60,6 +78,9 @@ void CPDF_LinkExtract::ParseLink() {
       }
       start = ++pos;
     } else {
+      bAfterHyphen = (pageChar.m_Flag == FPDFTEXT_CHAR_HYPHEN ||
+                      (pageChar.m_Flag == FPDFTEXT_CHAR_NORMAL &&
+                       pageChar.m_Unicode == TEXT_HYPHEN_CHAR));
       pos++;
     }
   }
diff --git a/core/fpdftext/cpdf_textpage.h b/core/fpdftext/cpdf_textpage.h
index ebe58eb7ff..d7e29edf3b 100644
--- a/core/fpdftext/cpdf_textpage.h
+++ b/core/fpdftext/cpdf_textpage.h
@@ -34,10 +34,12 @@ class CPDF_TextObject;
 #define TEXT_SPACE_CHAR L' '
 #define TEXT_LINEFEED_CHAR L'\n'
 #define TEXT_RETURN_CHAR L'\r'
+#define TEXT_HYPHEN_CHAR L'-'
 #define TEXT_EMPTY L""
 #define TEXT_SPACE L" "
 #define TEXT_RETURN_LINEFEED L"\r\n"
 #define TEXT_LINEFEED L"\n"
+#define TEXT_HYPHEN L"-"
 #define TEXT_CHARRATIO_GAPDELTA 0.070
 
 enum class FPDFText_MarkedContent { Pass = 0, Done, Delay };