[PATCH v5] wildmatch: properly fold case everywhere

[Anthony Ramine <n.oxyde@gmail.com>]

Case folding is not done correctly when matching against the [:upper:]
character class and uppercased character ranges (e.g. A-Z).
Specifically, an uppercase letter fails to match against any of them
when case folding is requested because plain characters in the pattern
and the whole string are preemptively lowercased to handle the base case
fast.

That optimization is kept and ISLOWER() is used in the [:upper:] case
when case folding is requested, while matching against a character range
is retried with toupper() if the character was lowercase, as the bounds
of the range itself cannot be modified (in a case-insensitive context,
[A-_] is not equivalent to [a-_]).

Signed-off-by: Anthony Ramine <n.oxyde@gmail.com>
Reviewed-by: Duy Nguyen <pclouds@gmail.com>
---
 t/t3070-wildmatch.sh | 55 ++++++++++++++++++++++++++++++++++++++++++++++------
 wildmatch.c          |  7 +++++++
 2 files changed, 56 insertions(+), 6 deletions(-)

I added Duy as reviewer and fixed a typo in the commit message reported by
Eric Sunshine.

diff --git a/t/t3070-wildmatch.sh b/t/t3070-wildmatch.sh
index 4c37057..38446a0 100755
--- a/t/t3070-wildmatch.sh
+++ b/t/t3070-wildmatch.sh
@@ -6,20 +6,20 @@ test_description='wildmatch tests'
 
 match() {
     if [ $1 = 1 ]; then
-	test_expect_success "wildmatch:    match '$3' '$4'" "
+	test_expect_success "wildmatch:     match '$3' '$4'" "
 	    test-wildmatch wildmatch '$3' '$4'
 	"
     else
-	test_expect_success "wildmatch: no match '$3' '$4'" "
+	test_expect_success "wildmatch:  no match '$3' '$4'" "
 	    ! test-wildmatch wildmatch '$3' '$4'
 	"
     fi
     if [ $2 = 1 ]; then
-	test_expect_success "fnmatch:      match '$3' '$4'" "
+	test_expect_success "fnmatch:       match '$3' '$4'" "
 	    test-wildmatch fnmatch '$3' '$4'
 	"
     elif [ $2 = 0 ]; then
-	test_expect_success "fnmatch:   no match '$3' '$4'" "
+	test_expect_success "fnmatch:    no match '$3' '$4'" "
 	    ! test-wildmatch fnmatch '$3' '$4'
 	"
 #    else
@@ -29,13 +29,25 @@ match() {
     fi
 }
 
+imatch() {
+    if [ $1 = 1 ]; then
+	test_expect_success "iwildmatch:    match '$2' '$3'" "
+	    test-wildmatch iwildmatch '$2' '$3'
+	"
+    else
+	test_expect_success "iwildmatch: no match '$2' '$3'" "
+	    ! test-wildmatch iwildmatch '$2' '$3'
+	"
+    fi
+}
+
 pathmatch() {
     if [ $1 = 1 ]; then
-	test_expect_success "pathmatch:    match '$2' '$3'" "
+	test_expect_success "pathmatch:     match '$2' '$3'" "
 	    test-wildmatch pathmatch '$2' '$3'
 	"
     else
-	test_expect_success "pathmatch: no match '$2' '$3'" "
+	test_expect_success "pathmatch:  no match '$2' '$3'" "
 	    ! test-wildmatch pathmatch '$2' '$3'
 	"
     fi
@@ -235,4 +247,35 @@ pathmatch 1 abcXdefXghi '*X*i'
 pathmatch 1 ab/cXd/efXg/hi '*/*X*/*/*i'
 pathmatch 1 ab/cXd/efXg/hi '*Xg*i'
 
+# Case-sensitivy features
+match 0 x 'a' '[A-Z]'
+match 1 x 'A' '[A-Z]'
+match 0 x 'A' '[a-z]'
+match 1 x 'a' '[a-z]'
+match 0 x 'a' '[[:upper:]]'
+match 1 x 'A' '[[:upper:]]'
+match 0 x 'A' '[[:lower:]]'
+match 1 x 'a' '[[:lower:]]'
+match 0 x 'A' '[B-Za]'
+match 1 x 'a' '[B-Za]'
+match 0 x 'A' '[B-a]'
+match 1 x 'a' '[B-a]'
+match 0 x 'z' '[Z-y]'
+match 1 x 'Z' '[Z-y]'
+
+imatch 1 'a' '[A-Z]'
+imatch 1 'A' '[A-Z]'
+imatch 1 'A' '[a-z]'
+imatch 1 'a' '[a-z]'
+imatch 1 'a' '[[:upper:]]'
+imatch 1 'A' '[[:upper:]]'
+imatch 1 'A' '[[:lower:]]'
+imatch 1 'a' '[[:lower:]]'
+imatch 1 'A' '[B-Za]'
+imatch 1 'a' '[B-Za]'
+imatch 1 'A' '[B-a]'
+imatch 1 'a' '[B-a]'
+imatch 1 'z' '[Z-y]'
+imatch 1 'Z' '[Z-y]'
+
 test_done
diff --git a/wildmatch.c b/wildmatch.c
index 7192bdc..f91ba99 100644
--- a/wildmatch.c
+++ b/wildmatch.c
@@ -196,6 +196,11 @@ static int dowild(const uchar *p, const uchar *text, unsigned int flags)
 					}
 					if (t_ch <= p_ch && t_ch >= prev_ch)
 						matched = 1;
+					else if ((flags & WM_CASEFOLD) && ISLOWER(t_ch)) {
+						uchar t_ch_upper = toupper(t_ch);
+						if (t_ch_upper <= p_ch && t_ch_upper >= prev_ch)
+							matched = 1;
+					}
 					p_ch = 0; /* This makes "prev_ch" get set to 0. */
 				} else if (p_ch == '[' && p[1] == ':') {
 					const uchar *s;
@@ -245,6 +250,8 @@ static int dowild(const uchar *p, const uchar *text, unsigned int flags)
 					} else if (CC_EQ(s,i, "upper")) {
 						if (ISUPPER(t_ch))
 							matched = 1;
+						else if ((flags & WM_CASEFOLD) && ISLOWER(t_ch))
+							matched = 1;
 					} else if (CC_EQ(s,i, "xdigit")) {
 						if (ISXDIGIT(t_ch))
 							matched = 1;
-- 
1.8.3