summaryrefslogtreecommitdiff
path: root/testdata
diff options
context:
space:
mode:
authorph10 <ph10@6239d852-aaf2-0410-a92c-79f79f948069>2019-09-10 15:38:42 +0000
committerph10 <ph10@6239d852-aaf2-0410-a92c-79f79f948069>2019-09-10 15:38:42 +0000
commit254a2966b3ddfacf34e83ccc4313b50320164be7 (patch)
tree95b352ddd8c10aeaf1e6a5a06d361485fb5c26ce /testdata
parent2f211cde4ba45a9827eae1d00b13c179ba658aa5 (diff)
downloadpcre2-254a2966b3ddfacf34e83ccc4313b50320164be7.tar.gz
Improve starting-byte bit map for UTF-8 patterns with wide characters in
classes. git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@1170 6239d852-aaf2-0410-a92c-79f79f948069
Diffstat (limited to 'testdata')
-rw-r--r--testdata/testinput106
-rw-r--r--testdata/testoutput1066
2 files changed, 37 insertions, 35 deletions
diff --git a/testdata/testinput10 b/testdata/testinput10
index 4353119..cf92525 100644
--- a/testdata/testinput10
+++ b/testdata/testinput10
@@ -561,4 +561,10 @@
/[\x{c1}\x{e1}]X[\x{145}\x{146}]/I,utf
+/[󿾟,]/BI,utf
+
+/[\x{fff4}-\x{ffff8}]/I,utf
+
+/[\x{fff4}-\x{afff8}\x{10ffff}]/I,utf
+
# End of testinput10
diff --git a/testdata/testoutput10 b/testdata/testoutput10
index e5c7d3c..1fe44fb 100644
--- a/testdata/testoutput10
+++ b/testdata/testoutput10
@@ -1256,11 +1256,7 @@ Subject length lower bound = 1
------------------------------------------------------------------
Capture group count = 0
Options: utf
-Starting code units: Z \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd
- \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc
- \xdd \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb
- \xec \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa
- \xfb \xfc \xfd \xfe \xff
+Starting code units: Z \xc4
Subject length lower bound = 1
Z\x{100}
0: Z
@@ -1278,11 +1274,7 @@ Subject length lower bound = 1
------------------------------------------------------------------
Capture group count = 0
Options: utf
-Starting code units: z { | } ~ \x7f \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9
- \xca \xcb \xcc \xcd \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8
- \xd9 \xda \xdb \xdc \xdd \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7
- \xe8 \xe9 \xea \xeb \xec \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6
- \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd \xfe \xff
+Starting code units: z { | } ~ \x7f \xc2 \xc3 \xc4
Subject length lower bound = 1
/[z\Qa-d]Ā\E]/IB,utf
@@ -1294,11 +1286,7 @@ Subject length lower bound = 1
------------------------------------------------------------------
Capture group count = 0
Options: utf
-Starting code units: - ] a d z \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc
- \xcd \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb
- \xdc \xdd \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea
- \xeb \xec \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9
- \xfa \xfb \xfc \xfd \xfe \xff
+Starting code units: - ] a d z \xc4
Subject length lower bound = 1
\x{100}
0: \x{100}
@@ -1319,11 +1307,7 @@ Subject length lower bound = 1
------------------------------------------------------------------
Capture group count = 1
Options: utf
-Starting code units: a b \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd
- \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc
- \xdd \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb
- \xec \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa
- \xfb \xfc \xfd \xfe \xff
+Starting code units: a b \xc4
Last code unit = 'z'
Subject length lower bound = 7
@@ -1440,11 +1424,7 @@ Subject length lower bound = 1
------------------------------------------------------------------
Capture group count = 0
Options: caseless utf
-Starting code units: \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce
- \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd
- \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec
- \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb
- \xfc \xfd \xfe \xff
+Starting code units: \xc4
Subject length lower bound = 1
\x{104}
0: \x{104}
@@ -1467,11 +1447,7 @@ No match
------------------------------------------------------------------
Capture group count = 0
Options: caseless utf
-Starting code units: Z z { | } ~ \x7f \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8
- \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7
- \xd8 \xd9 \xda \xdb \xdc \xdd \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6
- \xe7 \xe8 \xe9 \xea \xeb \xec \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5
- \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd \xfe \xff
+Starting code units: Z z { | } ~ \x7f \xc2 \xc3 \xc4 \xc5 \xce \xe1 \xe2
Subject length lower bound = 1
Z
0: Z
@@ -1508,11 +1484,7 @@ No match
------------------------------------------------------------------
Capture group count = 0
Options: caseless utf
-Starting code units: Z z { | } ~ \x7f \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8
- \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7
- \xd8 \xd9 \xda \xdb \xdc \xdd \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6
- \xe7 \xe8 \xe9 \xea \xeb \xec \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5
- \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd \xfe \xff
+Starting code units: Z z { | } ~ \x7f \xc2 \xc3 \xc4 \xc5 \xce \xe1 \xe2
Subject length lower bound = 1
/\x{3a3}B/IBi,utf
@@ -1773,4 +1745,28 @@ Starting code units: \xc3
Last code unit = 'X'
Subject length lower bound = 3
+/[󿾟,]/BI,utf
+------------------------------------------------------------------
+ Bra
+ [,\x{fff9f}]
+ Ket
+ End
+------------------------------------------------------------------
+Capture group count = 0
+Options: utf
+Starting code units: , \xf3
+Subject length lower bound = 1
+
+/[\x{fff4}-\x{ffff8}]/I,utf
+Capture group count = 0
+Options: utf
+Starting code units: \xef \xf0 \xf1 \xf2 \xf3
+Subject length lower bound = 1
+
+/[\x{fff4}-\x{afff8}\x{10ffff}]/I,utf
+Capture group count = 0
+Options: utf
+Starting code units: \xef \xf0 \xf1 \xf2 \xf4
+Subject length lower bound = 1
+
# End of testinput10