diff options
author | Tom Tromey <tromey@redhat.com> | 2006-04-17 21:41:47 +0000 |
---|---|---|
committer | Tom Tromey <tromey@gcc.gnu.org> | 2006-04-17 21:41:47 +0000 |
commit | dff81d4f4cf9c3dd98c8e72da0f63799a6620abf (patch) | |
tree | 5f0e83a1d9485d115be3948513876390201dac34 /libjava/gnu/gcj | |
parent | e26303c2f718f8b5dec468efdf49e0d50e31e813 (diff) | |
download | gcc-dff81d4f4cf9c3dd98c8e72da0f63799a6620abf.zip gcc-dff81d4f4cf9c3dd98c8e72da0f63799a6620abf.tar.gz gcc-dff81d4f4cf9c3dd98c8e72da0f63799a6620abf.tar.bz2 |
re PR libgcj/27171 (UTF8 PrintWriter goes haywire)
PR libgcj/27171:
* testsuite/libjava.lang/pr27171.java: New file.
* testsuite/libjava.lang/pr27171.out: New file.
* gnu/gcj/convert/Output_UTF8.java (havePendingBytes): Return
true if we've seen a high surrogate.
(write): Handle high surrogates at the end of the stream.
Properly emit isolated low surrogates.
From-SVN: r113013
Diffstat (limited to 'libjava/gnu/gcj')
-rw-r--r-- | libjava/gnu/gcj/convert/Output_UTF8.java | 34 |
1 files changed, 26 insertions, 8 deletions
diff --git a/libjava/gnu/gcj/convert/Output_UTF8.java b/libjava/gnu/gcj/convert/Output_UTF8.java index f54e7eb..e550a7f 100644 --- a/libjava/gnu/gcj/convert/Output_UTF8.java +++ b/libjava/gnu/gcj/convert/Output_UTF8.java @@ -1,4 +1,4 @@ -/* Copyright (C) 1999, 2000, 2003 Free Software Foundation +/* Copyright (C) 1999, 2000, 2003, 2006 Free Software Foundation This file is part of libgcj. @@ -36,7 +36,7 @@ public class Output_UTF8 extends UnicodeToBytes int avail = buf.length - count; for (;;) { - if (avail == 0 || (inlength == 0 && bytes_todo == 0)) + if (avail == 0 || (inlength == 0 && bytes_todo == 0 && hi_part == 0)) break; // The algorithm is made more complicated because we want to write // at least one byte in the output buffer, if there is room for @@ -61,17 +61,25 @@ public class Output_UTF8 extends UnicodeToBytes continue; } + // Handle a high surrogate at the end of the input stream. + if (inlength == 0 && hi_part != 0) + { + buf[count++] = (byte) (0xE0 | (hi_part >> 12)); + value = hi_part; + hi_part = 0; + avail--; + bytes_todo = 2; + continue; + } + char ch = inbuffer[inpos++]; inlength--; - if ((hi_part != 0 && (ch <= 0xDBFF || ch > 0xDFFF)) - || (hi_part == 0 && ch >= 0xDC00 && ch <= 0xDFFF)) + if (hi_part != 0 && (ch <= 0xDBFF || ch > 0xDFFF)) { // If the previous character was a high surrogate, and we // don't now have a low surrogate, we print the high - // surrogate as an isolated character. If this character - // is a low surrogate and we didn't previously see a high - // surrogate, we do the same thing. + // surrogate as an isolated character. --inpos; ++inlength; buf[count++] = (byte) (0xE0 | (hi_part >> 12)); @@ -80,6 +88,16 @@ public class Output_UTF8 extends UnicodeToBytes avail--; bytes_todo = 2; } + else if (hi_part == 0 && ch >= 0xDC00 && ch <= 0xDFFF) + { + // If this character is a low surrogate and we didn't + // previously see a high surrogate, we do the same thing + // as above. + buf[count++] = (byte) (0xE0 | (ch >> 12)); + value = ch; + avail--; + bytes_todo = 2; + } else if (ch < 128 && (ch != 0 || standardUTF8)) { avail--; @@ -122,7 +140,7 @@ public class Output_UTF8 extends UnicodeToBytes public boolean havePendingBytes() { - return bytes_todo > 0; + return bytes_todo > 0 || hi_part != 0; } } |