include/rtl/textcvt.h | 9 ++++++
sal/qa/rtl/textenc/rtl_textcvt.cxx | 2 -
sal/textenc/convertbig5hkscs.cxx | 22 +++++++++++++---
sal/textenc/converteuctw.cxx | 22 +++++++++++++---
sal/textenc/convertgb18030.cxx | 32 ++++++++++++++++++------
sal/textenc/convertisciidevangari.cxx | 19 ++++++++++----
sal/textenc/convertiso2022cn.cxx | 23 ++++++++++++++---
sal/textenc/convertiso2022jp.cxx | 18 ++++++++++++-
sal/textenc/convertiso2022kr.cxx | 17 +++++++++++--
sal/textenc/convertsimple.cxx | 3 ++
sal/textenc/convertsinglebytetobmpunicode.cxx | 3 ++
sal/textenc/tcvtmb.cxx | 34 ++++++++++++++++++++++++++
sal/textenc/tcvtutf7.cxx | 17 +++++++++++++
sal/textenc/tcvtutf8.cxx | 15 +++++++++--
14 files changed, 204 insertions(+), 32 deletions(-)
New commits:
commit ca6ddfcc9385f1c31531eae31dfa81a9dda246f0
Author: Stephan Bergmann <sberg...@redhat.com>
AuthorDate: Wed Sep 4 09:36:03 2019 +0200
Commit: Stephan Bergmann <sberg...@redhat.com>
CommitDate: Wed Sep 4 13:02:11 2019 +0200
[API CHANGE] rtl_convertTextToUnicode behavior upon erroneous input
<http://udk.openoffice.org/cpp/man/spec/textconversion.html> specifies that
FLAGS_UNDEFINED_ERROR, FLAGS_MBUNDEFINED_ERROR, and FLAGS_INVALID_ERROR:
"Read
past the [erroneous] code in the input buffer [...]" But actual behavior of
rtl_convertTextToUnicode for the various rtl_TextEncoding values has been
inconsistent. Some erroneous input (mostly single-byte UNDEFINED and
INVALID
ones) has not been consumed at all, some (multi-byte MBUNDEFINED and
INVALID)
has been consumed partly, and some has been consumed fully as required.
However, at least since 8dd4265b9ddbd7786b6237676909eae5b540da0e
"CWS-TOOLING:
integrate CWS hb18", Custom8BitToUnicode in sw/source/filter/ww8/ww8par.cxx
appears to rely on the broken behavior of not consuming erroneous input.
(It
reads the chunk of valid input with e.g. some RTL_TEXTENCODING_MS_125x that
happens to exhibit the broken behavior of not consuming erroneous input,
then
wants to try to re-read the erroneous input with RTL_TEXTENCODING_MS_1252.
For
example, opening sw/qa/core/data/ww8/pass/forcepoint50-grfanchor-1.doc
triggers
that code. For whatever reason, the am_faksas.dot attached to
<https://bz.apache.org/ooo/show_bug.cgi?id=9240#c1> "Do not show lithuanian
letter 'Š'" appears to not, or at least no longer, trigger that code.)
Therefore, it would be useful to have a mode in which
rtl_convertTextToUnicode
does not consume erroneous input. (And I plan on doing changes in
sal/osl/unx/file* that would benefit from that behavior, too.) But changing
rtl_convertTextToUnicode to generally not consume erroneous input would not
be
feasible: If calls do not set RTL_TEXTTOUNICODE_FLAGS_FLUSH, part of an
erroneous input can already have been consumed by a previous call, so the
current call cannot undo that.
But a change that looks like it can work is to change the behavior only if
RTL_TEXTTOUNICODE_FLAGS_FLUSH is set. In that case we can at least not
consume
the part of an erroneous input that has not yet been consumed by a previous
call
(which would necessarily have been done with RTL_TEXTTOUNICODE_FLAGS_FLUSH
unset). The expecation is that code that relies on the don't-consume
behavior
will do only single calls with RTL_TEXTTOUNICODE_FLAGS_FLUSH set (so
reliably
not consume the complete erroneous input), while other code (which might do
calls in a loop) will not care whether erroneous input has been consumed,
anyway. This can be considered a mild form of behavioral API CHANGE (but
note
that the old implementation didn't exhibit the requested behavior anyway).
So all implementations of rtl_convertTextToUnicode for the various
rtl_TextEncoding values have been adapted to the new behavior. The only
exceptions are ImplDummyToUnicode (sal/textenc/textcvt.cxx), which is a
special
case anyway used by RTL_TEXTENCODING_DONTKNOW, and two out of three places
(marked with a "TODO" each) in ImplUTF7ToUnicode (sal/textenc/tcvtutf7.cxx),
where it is hard to retrofit the expected behaivor, and
RTL_TEXTENCODING_UTF7 is
probably not relevant for the use cases relying on the
don't-consume--behavior,
anyway.
Whether a similar change should be done for rtl_convertUnicodeToText can be
examined later.
Change-Id: I1ac2c4cfd99e2a0eca219f9a3855ef110b254855
Reviewed-on: https://gerrit.libreoffice.org/78584
Tested-by: Jenkins
Reviewed-by: Stephan Bergmann <sberg...@redhat.com>
diff --git a/include/rtl/textcvt.h b/include/rtl/textcvt.h
index 09c33b1cb0ed..67e9f55e0f65 100644
--- a/include/rtl/textcvt.h
+++ b/include/rtl/textcvt.h
@@ -92,6 +92,15 @@ SAL_DLLPUBLIC void SAL_CALL rtl_resetTextToUnicodeContext(
rtl_TextToUnicodeConv
#define RTL_TEXTTOUNICODE_INFO_INVALID
((sal_uInt32)0x0020)
/** see http://udk.openoffice.org/cpp/man/spec/textconversion.html
+
+ Deviating from the linked specification, the behavior of
+ RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_ERROR,
RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_ERROR, and
+ RTL_TEXTTOUNICODE_FLAGS_INVALID_ERROR is as follows: When
RTL_TEXTTOUNICODE_FLAGS_FLUSH is not
+ set, the erroneous input bytes are consumed as required by the linked
specification. But if
+ RTL_TEXTTOUNICODE_FLAGS_FLUSH is set, any of those erroneous input bytes
that would have been
+ consumed by this invocation of rtl_convertTextToUnicode (i.e., which had
not already been
+ captured in hContext from a previous invocation with
RTL_TEXTTOUNICODE_FLAGS_FLUSH unset) are
+ not consumed.
*/
SAL_DLLPUBLIC sal_Size SAL_CALL rtl_convertTextToUnicode(
rtl_TextToUnicodeConverter
hConverter,
diff --git a/sal/qa/rtl/textenc/rtl_textcvt.cxx
b/sal/qa/rtl/textenc/rtl_textcvt.cxx
index 6b5a7e55fe21..2f5359b32c77 100644
--- a/sal/qa/rtl/textenc/rtl_textcvt.cxx
+++ b/sal/qa/rtl/textenc/rtl_textcvt.cxx
@@ -165,7 +165,7 @@ void testSingleByteCharSet(SingleByteCharSet const & rSet) {
CPPUNIT_ASSERT_EQUAL(sal_Size(0), nSize);
CPPUNIT_ASSERT_EQUAL(nExpectedInfo, nInfo);
- CPPUNIT_ASSERT_EQUAL(sal_Size(0), nConverted);
+ CPPUNIT_ASSERT_EQUAL(sal_Size(1), nConverted);
rtl_destroyTextToUnicodeContext(aConverter, aContext);
rtl_destroyTextToUnicodeConverter(aConverter);
diff --git a/sal/textenc/convertbig5hkscs.cxx b/sal/textenc/convertbig5hkscs.cxx
index 3d66bdfcc432..eaed0c7a36d2 100644
--- a/sal/textenc/convertbig5hkscs.cxx
+++ b/sal/textenc/convertbig5hkscs.cxx
@@ -82,6 +82,7 @@ sal_Size ImplConvertBig5HkscsToUnicode(void const * pData,
sal_Size nConverted = 0;
sal_Unicode * pDestBufPtr = pDestBuf;
sal_Unicode * pDestBufEnd = pDestBuf + nDestChars;
+ sal_Size startOfCurrentChar = 0;
if (pContext)
nRow = static_cast< ImplBig5HkscsToUnicodeContext *
>(pContext)->m_nRow;
@@ -92,9 +93,10 @@ sal_Size ImplConvertBig5HkscsToUnicode(void const * pData,
sal_uInt32 nChar = *reinterpret_cast<unsigned char const *>(pSrcBuf++);
if (nRow == 0)
if (nChar < 0x80)
- if (pDestBufPtr != pDestBufEnd)
+ if (pDestBufPtr != pDestBufEnd) {
*pDestBufPtr++ = static_cast<sal_Unicode>(nChar);
- else
+ startOfCurrentChar = nConverted + 1;
+ } else
goto no_output;
else if (nChar >= 0x81 && nChar <= 0xFE)
nRow = nChar;
@@ -202,13 +204,15 @@ sal_Size ImplConvertBig5HkscsToUnicode(void const * pData,
*pDestBufPtr++
= static_cast<sal_Unicode>(pBig5Hkscs2001Data[
nOffset + (nChar - nFirst)]);
+ startOfCurrentChar = nConverted + 1;
}
else
goto no_output;
else
- if (pDestBufPtr != pDestBufEnd)
+ if (pDestBufPtr != pDestBufEnd) {
*pDestBufPtr++ = static_cast<sal_Unicode>(nUnicode);
- else
+ startOfCurrentChar = nConverted + 1;
+ } else
goto no_output;
nRow = 0;
}
@@ -226,10 +230,16 @@ sal_Size ImplConvertBig5HkscsToUnicode(void const * pData,
{
case sal::detail::textenc::BAD_INPUT_STOP:
nRow = 0;
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ ++nConverted;
+ } else {
+ nConverted = startOfCurrentChar;
+ }
break;
case sal::detail::textenc::BAD_INPUT_CONTINUE:
nRow = 0;
+ startOfCurrentChar = nConverted + 1;
continue;
case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
@@ -256,6 +266,10 @@ sal_Size ImplConvertBig5HkscsToUnicode(void const * pData,
&nInfo))
{
case sal::detail::textenc::BAD_INPUT_STOP:
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) != 0) {
+ nConverted = startOfCurrentChar;
+ }
+ [[fallthrough]];
case sal::detail::textenc::BAD_INPUT_CONTINUE:
nRow = 0;
break;
diff --git a/sal/textenc/converteuctw.cxx b/sal/textenc/converteuctw.cxx
index 87becd9b11ec..abc214402636 100644
--- a/sal/textenc/converteuctw.cxx
+++ b/sal/textenc/converteuctw.cxx
@@ -93,6 +93,7 @@ sal_Size ImplConvertEucTwToUnicode(void const * pData,
sal_Size nConverted = 0;
sal_Unicode * pDestBufPtr = pDestBuf;
sal_Unicode * pDestBufEnd = pDestBuf + nDestChars;
+ sal_Size startOfCurrentChar = 0;
if (pContext)
{
@@ -109,9 +110,10 @@ sal_Size ImplConvertEucTwToUnicode(void const * pData,
{
case IMPL_EUC_TW_TO_UNICODE_STATE_0:
if (nChar < 0x80)
- if (pDestBufPtr != pDestBufEnd)
+ if (pDestBufPtr != pDestBufEnd) {
*pDestBufPtr++ = static_cast<sal_Unicode>(nChar);
- else
+ startOfCurrentChar = nConverted + 1;
+ } else
goto no_output;
else if (nChar >= 0xA1 && nChar <= 0xFE)
{
@@ -210,13 +212,15 @@ sal_Size ImplConvertEucTwToUnicode(void const * pData,
*pDestBufPtr++
=
static_cast<sal_Unicode>(pCns116431992Data[
nOffset + (nChar - nFirst)]);
+ startOfCurrentChar = nConverted + 1;
}
else
goto no_output;
else
- if (pDestBufPtr != pDestBufEnd)
+ if (pDestBufPtr != pDestBufEnd) {
*pDestBufPtr++ =
static_cast<sal_Unicode>(nUnicode);
- else
+ startOfCurrentChar = nConverted + 1;
+ } else
goto no_output;
}
else
@@ -234,10 +238,16 @@ sal_Size ImplConvertEucTwToUnicode(void const * pData,
{
case sal::detail::textenc::BAD_INPUT_STOP:
eState = IMPL_EUC_TW_TO_UNICODE_STATE_0;
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ ++nConverted;
+ } else {
+ nConverted = startOfCurrentChar;
+ }
break;
case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_EUC_TW_TO_UNICODE_STATE_0;
+ startOfCurrentChar = nConverted + 1;
continue;
case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
@@ -264,6 +274,10 @@ sal_Size ImplConvertEucTwToUnicode(void const * pData,
&nInfo))
{
case sal::detail::textenc::BAD_INPUT_STOP:
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) != 0) {
+ nConverted = startOfCurrentChar;
+ }
+ [[fallthrough]];
case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_EUC_TW_TO_UNICODE_STATE_0;
break;
diff --git a/sal/textenc/convertgb18030.cxx b/sal/textenc/convertgb18030.cxx
index 87e814674bb7..9aa64970421b 100644
--- a/sal/textenc/convertgb18030.cxx
+++ b/sal/textenc/convertgb18030.cxx
@@ -86,6 +86,7 @@ sal_Size ImplConvertGb18030ToUnicode(void const * pData,
sal_Size nConverted = 0;
sal_Unicode * pDestBufPtr = pDestBuf;
sal_Unicode * pDestBufEnd = pDestBuf + nDestChars;
+ sal_Size startOfCurrentChar = 0;
if (pContext)
{
@@ -101,9 +102,10 @@ sal_Size ImplConvertGb18030ToUnicode(void const * pData,
{
case IMPL_GB_18030_TO_UNICODE_STATE_0:
if (nChar < 0x80)
- if (pDestBufPtr != pDestBufEnd)
+ if (pDestBufPtr != pDestBufEnd) {
*pDestBufPtr++ = static_cast<sal_Unicode>(nChar);
- else
+ startOfCurrentChar = nConverted + 1;
+ } else
goto no_output;
else if (nChar == 0x80)
goto bad_input;
@@ -130,9 +132,10 @@ sal_Size ImplConvertGb18030ToUnicode(void const * pData,
{
nCode = nCode * 190 + (nChar <= 0x7E ? nChar - 0x40 :
nChar - 0x80 + 63);
- if (pDestBufPtr != pDestBufEnd)
+ if (pDestBufPtr != pDestBufEnd) {
*pDestBufPtr++ = pGb18030Data[nCode];
- else
+ startOfCurrentChar = nConverted + 1;
+ } else
goto no_output;
eState = IMPL_GB_18030_TO_UNICODE_STATE_0;
}
@@ -170,6 +173,7 @@ sal_Size ImplConvertGb18030ToUnicode(void const * pData,
=
static_cast<sal_Unicode>(ImplGetHighSurrogate(nCode));
*pDestBufPtr++
=
static_cast<sal_Unicode>(ImplGetLowSurrogate(nCode));
+ startOfCurrentChar = nConverted + 1;
}
else
goto no_output;
@@ -184,24 +188,26 @@ sal_Size ImplConvertGb18030ToUnicode(void const * pData,
goto bad_input;
else if (nCode < pRange->m_nFirstLinear)
{
- if (pDestBufPtr != pDestBufEnd)
+ if (pDestBufPtr != pDestBufEnd) {
*pDestBufPtr++
= pGb18030Data[
pRange->m_nNonRangeDataIndex
+ (nCode - nFirstNonRange)];
- else
+ startOfCurrentChar = nConverted + 1;
+ } else
goto no_output;
break;
}
else if (nCode < pRange->m_nPastLinear)
{
- if (pDestBufPtr != pDestBufEnd)
+ if (pDestBufPtr != pDestBufEnd) {
*pDestBufPtr++
=
static_cast<sal_Unicode>(pRange->m_nFirstUnicode
+ (nCode
- pRange->
m_nFirstLinear));
- else
+ startOfCurrentChar = nConverted + 1;
+ } else
goto no_output;
break;
}
@@ -226,10 +232,16 @@ sal_Size ImplConvertGb18030ToUnicode(void const * pData,
{
case sal::detail::textenc::BAD_INPUT_STOP:
eState = IMPL_GB_18030_TO_UNICODE_STATE_0;
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ ++nConverted;
+ } else {
+ nConverted = startOfCurrentChar;
+ }
break;
case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_GB_18030_TO_UNICODE_STATE_0;
+ startOfCurrentChar = nConverted + 1;
continue;
case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
@@ -256,6 +268,10 @@ sal_Size ImplConvertGb18030ToUnicode(void const * pData,
&nInfo))
{
case sal::detail::textenc::BAD_INPUT_STOP:
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) != 0) {
+ nConverted = startOfCurrentChar;
+ }
+ [[fallthrough]];
case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_GB_18030_TO_UNICODE_STATE_0;
break;
diff --git a/sal/textenc/convertisciidevangari.cxx
b/sal/textenc/convertisciidevangari.cxx
index 16c453fb8487..9e6583119252 100644
--- a/sal/textenc/convertisciidevangari.cxx
+++ b/sal/textenc/convertisciidevangari.cxx
@@ -96,6 +96,7 @@ sal_Size IsciiDevanagariToUnicode::convert(
sal_Size nConverted = 0;
sal_Unicode* pDestBufPtr = pDestBuf;
sal_Unicode* pDestBufEnd = pDestBuf + nDestChars;
+ sal_Size startOfCurrentChar = 0;
while (nConverted < nSrcBytes)
{
@@ -180,6 +181,10 @@ sal_Size IsciiDevanagariToUnicode::convert(
}
}
+ ++nConverted;
+ if (bDouble)
+ ++nConverted;
+
if (bNormal)
cChar = IsciiDevanagariMap[nIn];
@@ -190,20 +195,24 @@ sal_Size IsciiDevanagariToUnicode::convert(
BadInputConversionAction eAction =
handleBadInputTextToUnicodeConversion(
bUndefined, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
&nInfo);
- if (eAction == BAD_INPUT_CONTINUE)
+ if (eAction == BAD_INPUT_CONTINUE) {
+ startOfCurrentChar = nConverted;
continue;
- if (eAction == BAD_INPUT_STOP)
+ }
+ if (eAction == BAD_INPUT_STOP) {
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) != 0) {
+ nConverted = startOfCurrentChar;
+ }
break;
+ }
assert(eAction == BAD_INPUT_NO_OUTPUT);
nInfo |= RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOOSMALL;
break;
}
- ++nConverted;
- if (bDouble)
- ++nConverted;
*pDestBufPtr++ = cChar;
m_cPrevChar = bNormal ? nIn : 0;
+ startOfCurrentChar = nConverted;
}
if (pInfo)
diff --git a/sal/textenc/convertiso2022cn.cxx b/sal/textenc/convertiso2022cn.cxx
index e931d68f1f35..76aee21f04b4 100644
--- a/sal/textenc/convertiso2022cn.cxx
+++ b/sal/textenc/convertiso2022cn.cxx
@@ -124,6 +124,7 @@ sal_Size ImplConvertIso2022CnToUnicode(void const * pData,
sal_Size nConverted = 0;
sal_Unicode * pDestBufPtr = pDestBuf;
sal_Unicode * pDestBufEnd = pDestBuf + nDestChars;
+ sal_Size startOfCurrentChar = 0;
if (pContext)
{
@@ -149,9 +150,10 @@ sal_Size ImplConvertIso2022CnToUnicode(void const * pData,
else if (nChar == 0x1B) // ESC
eState = IMPL_ISO_2022_CN_TO_UNICODE_STATE_ESC;
else if (nChar < 0x80)
- if (pDestBufPtr != pDestBufEnd)
+ if (pDestBufPtr != pDestBufEnd) {
*pDestBufPtr++ = static_cast<sal_Unicode>(nChar);
- else
+ startOfCurrentChar = nConverted + 1;
+ } else
goto no_output;
else
{
@@ -203,6 +205,7 @@ sal_Size ImplConvertIso2022CnToUnicode(void const * pData,
{
*pDestBufPtr++ =
static_cast<sal_Unicode>(nUnicode);
eState = IMPL_ISO_2022_CN_TO_UNICODE_STATE_SO;
+ startOfCurrentChar = nConverted + 1;
}
else
goto no_output;
@@ -332,13 +335,15 @@ sal_Size ImplConvertIso2022CnToUnicode(void const * pData,
*pDestBufPtr++
=
static_cast<sal_Unicode>(pCns116431992Data[
nOffset + (nChar - nFirst)]);
+ startOfCurrentChar = nConverted + 1;
}
else
goto no_output;
else
- if (pDestBufPtr != pDestBufEnd)
+ if (pDestBufPtr != pDestBufEnd) {
*pDestBufPtr++ =
static_cast<sal_Unicode>(nUnicode);
- else
+ startOfCurrentChar = nConverted + 1;
+ } else
goto no_output;
}
else
@@ -358,11 +363,17 @@ sal_Size ImplConvertIso2022CnToUnicode(void const * pData,
case sal::detail::textenc::BAD_INPUT_STOP:
eState = IMPL_ISO_2022_CN_TO_UNICODE_STATE_ASCII;
b116431 = false;
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ ++nConverted;
+ } else {
+ nConverted = startOfCurrentChar;
+ }
break;
case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_ISO_2022_CN_TO_UNICODE_STATE_ASCII;
b116431 = false;
+ startOfCurrentChar = nConverted + 1;
continue;
case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
@@ -389,6 +400,10 @@ sal_Size ImplConvertIso2022CnToUnicode(void const * pData,
&nInfo))
{
case sal::detail::textenc::BAD_INPUT_STOP:
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) != 0) {
+ nConverted = startOfCurrentChar;
+ }
+ [[fallthrough]];
case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_ISO_2022_CN_TO_UNICODE_STATE_ASCII;
b116431 = false;
diff --git a/sal/textenc/convertiso2022jp.cxx b/sal/textenc/convertiso2022jp.cxx
index f0eb5eb9a936..565c09ab36f5 100644
--- a/sal/textenc/convertiso2022jp.cxx
+++ b/sal/textenc/convertiso2022jp.cxx
@@ -94,6 +94,7 @@ sal_Size ImplConvertIso2022JpToUnicode(void const * pData,
sal_Size nConverted = 0;
sal_Unicode * pDestBufPtr = pDestBuf;
sal_Unicode * pDestBufEnd = pDestBuf + nDestChars;
+ sal_Size startOfCurrentChar = 0;
if (pContext)
{
@@ -111,9 +112,10 @@ sal_Size ImplConvertIso2022JpToUnicode(void const * pData,
if (nChar == 0x1B) // ESC
eState = IMPL_ISO_2022_JP_TO_UNICODE_STATE_ESC;
else if (nChar < 0x80)
- if (pDestBufPtr != pDestBufEnd)
+ if (pDestBufPtr != pDestBufEnd) {
*pDestBufPtr++ = static_cast<sal_Unicode>(nChar);
- else
+ startOfCurrentChar = nConverted + 1;
+ } else
goto no_output;
else
{
@@ -139,6 +141,7 @@ sal_Size ImplConvertIso2022JpToUnicode(void const * pData,
break;
}
*pDestBufPtr++ = static_cast<sal_Unicode>(nChar);
+ startOfCurrentChar = nConverted + 1;
}
else
goto no_output;
@@ -178,6 +181,7 @@ sal_Size ImplConvertIso2022JpToUnicode(void const * pData,
{
*pDestBufPtr++ = static_cast<sal_Unicode>(nUnicode);
eState = IMPL_ISO_2022_JP_TO_UNICODE_STATE_0208;
+ startOfCurrentChar = nConverted + 1;
}
else
goto no_output;
@@ -248,10 +252,16 @@ sal_Size ImplConvertIso2022JpToUnicode(void const * pData,
{
case sal::detail::textenc::BAD_INPUT_STOP:
eState = IMPL_ISO_2022_JP_TO_UNICODE_STATE_ASCII;
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ ++nConverted;
+ } else {
+ nConverted = startOfCurrentChar;
+ }
break;
case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_ISO_2022_JP_TO_UNICODE_STATE_ASCII;
+ startOfCurrentChar = nConverted + 1;
continue;
case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
@@ -278,6 +288,10 @@ sal_Size ImplConvertIso2022JpToUnicode(void const * pData,
&nInfo))
{
case sal::detail::textenc::BAD_INPUT_STOP:
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) != 0) {
+ nConverted = startOfCurrentChar;
+ }
+ [[fallthrough]];
case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_ISO_2022_JP_TO_UNICODE_STATE_ASCII;
break;
diff --git a/sal/textenc/convertiso2022kr.cxx b/sal/textenc/convertiso2022kr.cxx
index c65bc8597414..6169969812d2 100644
--- a/sal/textenc/convertiso2022kr.cxx
+++ b/sal/textenc/convertiso2022kr.cxx
@@ -100,6 +100,7 @@ sal_Size ImplConvertIso2022KrToUnicode(void const * pData,
sal_Size nConverted = 0;
sal_Unicode * pDestBufPtr = pDestBuf;
sal_Unicode * pDestBufEnd = pDestBuf + nDestChars;
+ sal_Size startOfCurrentChar = 0;
if (pContext)
{
@@ -119,9 +120,10 @@ sal_Size ImplConvertIso2022KrToUnicode(void const * pData,
else if (nChar == 0x1B) // ESC
eState = IMPL_ISO_2022_KR_TO_UNICODE_STATE_ESC;
else if (nChar < 0x80)
- if (pDestBufPtr != pDestBufEnd)
+ if (pDestBufPtr != pDestBufEnd) {
*pDestBufPtr++ = static_cast<sal_Unicode>(nChar);
- else
+ startOfCurrentChar = nConverted + 1;
+ } else
goto no_output;
else
{
@@ -159,6 +161,7 @@ sal_Size ImplConvertIso2022KrToUnicode(void const * pData,
{
*pDestBufPtr++ = static_cast<sal_Unicode>(nUnicode);
eState = IMPL_ISO_2022_KR_TO_UNICODE_STATE_1001;
+ startOfCurrentChar = nConverted + 1;
}
else
goto no_output;
@@ -211,10 +214,16 @@ sal_Size ImplConvertIso2022KrToUnicode(void const * pData,
{
case sal::detail::textenc::BAD_INPUT_STOP:
eState = IMPL_ISO_2022_KR_TO_UNICODE_STATE_ASCII;
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ ++nConverted;
+ } else {
+ nConverted = startOfCurrentChar;
+ }
break;
case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_ISO_2022_KR_TO_UNICODE_STATE_ASCII;
+ startOfCurrentChar = nConverted + 1;
continue;
case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
@@ -241,6 +250,10 @@ sal_Size ImplConvertIso2022KrToUnicode(void const * pData,
&nInfo))
{
case sal::detail::textenc::BAD_INPUT_STOP:
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) != 0) {
+ nConverted = startOfCurrentChar;
+ }
+ [[fallthrough]];
case sal::detail::textenc::BAD_INPUT_CONTINUE:
eState = IMPL_ISO_2022_KR_TO_UNICODE_STATE_ASCII;
break;
diff --git a/sal/textenc/convertsimple.cxx b/sal/textenc/convertsimple.cxx
index 386c77ba80a8..9e4950edbac1 100644
--- a/sal/textenc/convertsimple.cxx
+++ b/sal/textenc/convertsimple.cxx
@@ -540,6 +540,9 @@ sal_Size sal::detail::textenc::convertCharToUnicode(
*pInfo |= RTL_TEXTTOUNICODE_INFO_UNDEFINED;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_MASK) ==
RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_ERROR )
{
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ ++pSrcBuf;
+ }
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
diff --git a/sal/textenc/convertsinglebytetobmpunicode.cxx
b/sal/textenc/convertsinglebytetobmpunicode.cxx
index 3458668a1f57..b883411cbffa 100644
--- a/sal/textenc/convertsinglebytetobmpunicode.cxx
+++ b/sal/textenc/convertsinglebytetobmpunicode.cxx
@@ -58,6 +58,9 @@ sal_Size rtl_textenc_convertSingleByteToBmpUnicode(
&infoFlags))
{
case sal::detail::textenc::BAD_INPUT_STOP:
+ if ((flags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ ++converted;
+ }
break;
case sal::detail::textenc::BAD_INPUT_CONTINUE:
diff --git a/sal/textenc/tcvtmb.cxx b/sal/textenc/tcvtmb.cxx
index 6faa56b7c362..4e990cc1e91e 100644
--- a/sal/textenc/tcvtmb.cxx
+++ b/sal/textenc/tcvtmb.cxx
@@ -43,6 +43,7 @@ sal_Size ImplDBCSToUnicode( const void* pData,
SAL_UNUSED_PARAMETER void*,
const ImplDBCSToUniLeadTab* pLeadTab = pConvertData->mpToUniLeadTab;
sal_Unicode* pEndDestBuf;
const char* pEndSrcBuf;
+ char const * startOfCurrentChar = pSrcBuf;
*pInfo = 0;
pEndDestBuf = pDestBuf+nDestChars;
@@ -65,12 +66,18 @@ sal_Size ImplDBCSToUnicode( const void* pData,
SAL_UNUSED_PARAMETER void*,
*pInfo |= RTL_TEXTTOUNICODE_INFO_UNDEFINED;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_MASK) ==
RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_ERROR )
{
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ ++pSrcBuf;
+ } else {
+ pSrcBuf = startOfCurrentChar;
+ }
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_MASK) ==
RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_IGNORE )
{
pSrcBuf++;
+ startOfCurrentChar = pSrcBuf;
continue;
}
cConv = ImplGetUndefinedUnicodeChar(cLead, nFlags);
@@ -158,12 +165,18 @@ sal_Size ImplDBCSToUnicode( const void* pData,
SAL_UNUSED_PARAMETER void*,
*pInfo |= RTL_TEXTTOUNICODE_INFO_INVALID;
if ( (nFlags &
RTL_TEXTTOUNICODE_FLAGS_INVALID_MASK) == RTL_TEXTTOUNICODE_FLAGS_INVALID_ERROR )
{
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH)
== 0) {
+ ++pSrcBuf;
+ } else {
+ pSrcBuf = startOfCurrentChar;
+ }
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
if ( (nFlags &
RTL_TEXTTOUNICODE_FLAGS_INVALID_MASK) == RTL_TEXTTOUNICODE_FLAGS_INVALID_IGNORE
)
{
pSrcBuf++;
+ startOfCurrentChar = pSrcBuf;
continue;
}
cConv = RTL_TEXTENC_UNICODE_REPLACEMENT_CHARACTER;
@@ -176,12 +189,18 @@ sal_Size ImplDBCSToUnicode( const void* pData,
SAL_UNUSED_PARAMETER void*,
*pInfo |= RTL_TEXTTOUNICODE_INFO_MBUNDEFINED;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_MASK) ==
RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_ERROR )
{
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ ++pSrcBuf;
+ } else {
+ pSrcBuf = startOfCurrentChar;
+ }
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_MASK) ==
RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_IGNORE )
{
pSrcBuf++;
+ startOfCurrentChar = pSrcBuf;
continue;
}
cConv = RTL_TEXTENC_UNICODE_REPLACEMENT_CHARACTER;
@@ -197,6 +216,7 @@ sal_Size ImplDBCSToUnicode( const void* pData,
SAL_UNUSED_PARAMETER void*,
*pDestBuf = cConv;
pDestBuf++;
pSrcBuf++;
+ startOfCurrentChar = pSrcBuf;
}
*pSrcCvtBytes = nSrcBytes - (pEndSrcBuf-pSrcBuf);
@@ -372,6 +392,7 @@ sal_Size ImplEUCJPToUnicode( const void* pData,
const ImplEUCJPConvertData* pConvertData = static_cast<const
ImplEUCJPConvertData*>(pData);
sal_Unicode* pEndDestBuf;
const char* pEndSrcBuf;
+ char const * startOfCurrentChar = pSrcBuf;
*pInfo = 0;
pEndDestBuf = pDestBuf+nDestChars;
@@ -471,18 +492,29 @@ sal_Size ImplEUCJPToUnicode( const void* pData,
*pInfo |= RTL_TEXTTOUNICODE_INFO_INVALID;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_INVALID_MASK) ==
RTL_TEXTTOUNICODE_FLAGS_INVALID_ERROR )
{
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ ++pSrcBuf;
+ } else {
+ pSrcBuf = startOfCurrentChar;
+ }
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_INVALID_MASK) ==
RTL_TEXTTOUNICODE_FLAGS_INVALID_IGNORE )
{
pSrcBuf++;
+ startOfCurrentChar = pSrcBuf;
continue;
}
cConv = RTL_TEXTENC_UNICODE_REPLACEMENT_CHARACTER;
}
else
{
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ ++pSrcBuf;
+ } else {
+ pSrcBuf = startOfCurrentChar;
+ }
*pInfo |= RTL_TEXTTOUNICODE_INFO_MBUNDEFINED;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_MASK)
== RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_ERROR )
{
@@ -492,6 +524,7 @@ sal_Size ImplEUCJPToUnicode( const void* pData,
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_MASK)
== RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_IGNORE )
{
pSrcBuf++;
+ startOfCurrentChar = pSrcBuf;
continue;
}
cConv = RTL_TEXTENC_UNICODE_REPLACEMENT_CHARACTER;
@@ -508,6 +541,7 @@ sal_Size ImplEUCJPToUnicode( const void* pData,
*pDestBuf = cConv;
pDestBuf++;
pSrcBuf++;
+ startOfCurrentChar = pSrcBuf;
}
*pSrcCvtBytes = nSrcBytes - (pEndSrcBuf-pSrcBuf);
diff --git a/sal/textenc/tcvtutf7.cxx b/sal/textenc/tcvtutf7.cxx
index dd97b213750b..b09ccd47f1d8 100644
--- a/sal/textenc/tcvtutf7.cxx
+++ b/sal/textenc/tcvtutf7.cxx
@@ -254,6 +254,13 @@ sal_Size ImplUTF7ToUnicode( SAL_UNUSED_PARAMETER const
void*, void* pContext,
*pInfo |= RTL_TEXTTOUNICODE_INFO_INVALID;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_INVALID_MASK)
== RTL_TEXTTOUNICODE_FLAGS_INVALID_ERROR )
{
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0)
{
+ if (!bEnd) {
+ ++pSrcBuf;
+ }
+ } else {
+ //TODO: move pSrcBuf back to a reasonable
starting place
+ }
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
@@ -303,6 +310,13 @@ sal_Size ImplUTF7ToUnicode( SAL_UNUSED_PARAMETER const
void*, void* pContext,
*pInfo |= RTL_TEXTTOUNICODE_INFO_INVALID;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_INVALID_MASK)
== RTL_TEXTTOUNICODE_FLAGS_INVALID_ERROR )
{
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0)
{
+ if (!bEnd) {
+ ++pSrcBuf;
+ }
+ } else {
+ //TODO: move pSrcBuf back to a reasonable
starting place
+ }
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
@@ -344,6 +358,9 @@ sal_Size ImplUTF7ToUnicode( SAL_UNUSED_PARAMETER const
void*, void* pContext,
*pInfo |= RTL_TEXTTOUNICODE_INFO_INVALID;
if ( (nFlags & RTL_TEXTTOUNICODE_FLAGS_INVALID_MASK)
== RTL_TEXTTOUNICODE_FLAGS_INVALID_ERROR )
{
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0)
{
+ ++pSrcBuf;
+ }
*pInfo |= RTL_TEXTTOUNICODE_INFO_ERROR;
break;
}
diff --git a/sal/textenc/tcvtutf8.cxx b/sal/textenc/tcvtutf8.cxx
index 72b336b9ded4..a2430ff7c075 100644
--- a/sal/textenc/tcvtutf8.cxx
+++ b/sal/textenc/tcvtutf8.cxx
@@ -76,6 +76,7 @@ sal_Size ImplConvertUtf8ToUnicode(
unsigned char const * pSrcBufEnd = pSrcBufPtr + nSrcBytes;
sal_Unicode * pDestBufPtr = pDestBuf;
sal_Unicode * pDestBufEnd = pDestBufPtr + nDestChars;
+ unsigned char const * startOfCurrentChar = pSrcBufPtr;
if (pContext != nullptr)
{
@@ -200,6 +201,7 @@ sal_Size ImplConvertUtf8ToUnicode(
}
nShift = -1;
bCheckBom = false;
+ startOfCurrentChar = pSrcBufPtr;
continue;
bad_input:
@@ -210,8 +212,12 @@ sal_Size ImplConvertUtf8ToUnicode(
case sal::detail::textenc::BAD_INPUT_STOP:
nShift = -1;
bCheckBom = false;
- if (!bConsume)
- --pSrcBufPtr;
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) == 0) {
+ if (!bConsume)
+ --pSrcBufPtr;
+ } else {
+ pSrcBufPtr = startOfCurrentChar;
+ }
break;
case sal::detail::textenc::BAD_INPUT_CONTINUE:
@@ -219,6 +225,7 @@ sal_Size ImplConvertUtf8ToUnicode(
bCheckBom = false;
if (!bConsume)
--pSrcBufPtr;
+ startOfCurrentChar = pSrcBufPtr;
continue;
case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
@@ -245,6 +252,10 @@ sal_Size ImplConvertUtf8ToUnicode(
&nInfo))
{
case sal::detail::textenc::BAD_INPUT_STOP:
+ if ((nFlags & RTL_TEXTTOUNICODE_FLAGS_FLUSH) != 0) {
+ pSrcBufPtr = startOfCurrentChar;
+ }
+ [[fallthrough]];
case sal::detail::textenc::BAD_INPUT_CONTINUE:
nShift = -1;
bCheckBom = false;
_______________________________________________
Libreoffice-commits mailing list
libreoffice-comm...@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/libreoffice-commits
