threads / patch / 44599

patch, 2 partsupdate-unicode.sh: automatically download newer definition files

Subject: [PATCH 1/2] update-unicode.sh: automatically download newer definition files

## tl;dr

18 messages between Dec 2, 2016 and Dec 7, 2016. Diffs are folded; open one to read it.

replies: 17people: 4as markdown or json

Beat Bolli· Dec 2, 2016, 21:26 UTC · lore

Checking just for the files' existence is not enough; we should also download them if a newer version exists on the Unicode servers.

Signed-off-by: Beat Bolli <dev+git@drbeat.li>
---
 update_unicode.sh | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

Show changes to update_unicode.sh +2 −6

diff --git a/update_unicode.sh b/update_unicode.sh
index 27af77c..3c84270 100755
--- a/update_unicode.sh
+++ b/update_unicode.sh
@@ -10,12 +10,8 @@ if ! test -d unicode; then
 	mkdir unicode
 fi &&
 ( cd unicode &&
-	if ! test -f UnicodeData.txt; then
-		wget http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
-	fi &&
-	if ! test -f EastAsianWidth.txt; then
-		wget http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt
-	fi &&
+	wget -N http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt \
+		http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt &&
 	if ! test -d uniset; then
 		git clone https://github.com/depp/uniset.git
 	fi &&

-- 
2.7.2

Beat Bolli· Dec 2, 2016, 21:26 UTC · re: Beat Bolli · lore

[PATCH 2/2] unicode: update the tables to Unicode 9.0

A rerun of the previously fixed update-unicode.sh produces these new tables.

Signed-off-by: Beat Bolli <dev+git@drbeat.li>
---
 unicode_width.h | 122 +++++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 111 insertions(+), 11 deletions(-)

Show changes to unicode_width.h +111 −11

diff --git a/unicode_width.h b/unicode_width.h
index 47cdd23..73b5fd6 100644
--- a/unicode_width.h
+++ b/unicode_width.h
@@ -25,7 +25,7 @@ static const struct interval zero_width[] = {
 { 0x0825, 0x0827 },
 { 0x0829, 0x082D },
 { 0x0859, 0x085B },
-{ 0x08E4, 0x0902 },
+{ 0x08D4, 0x0902 },
 { 0x093A, 0x093A },
 { 0x093C, 0x093C },
 { 0x0941, 0x0948 },
@@ -120,6 +120,7 @@ static const struct interval zero_width[] = {
 { 0x17C9, 0x17D3 },
 { 0x17DD, 0x17DD },
 { 0x180B, 0x180E },
+{ 0x1885, 0x1886 },
 { 0x18A9, 0x18A9 },
 { 0x1920, 0x1922 },
 { 0x1927, 0x1928 },
@@ -158,7 +159,7 @@ static const struct interval zero_width[] = {
 { 0x1CF4, 0x1CF4 },
 { 0x1CF8, 0x1CF9 },
 { 0x1DC0, 0x1DF5 },
-{ 0x1DFC, 0x1DFF },
+{ 0x1DFB, 0x1DFF },
 { 0x200B, 0x200F },
 { 0x202A, 0x202E },
 { 0x2060, 0x2064 },
@@ -171,13 +172,13 @@ static const struct interval zero_width[] = {
 { 0x3099, 0x309A },
 { 0xA66F, 0xA672 },
 { 0xA674, 0xA67D },
-{ 0xA69F, 0xA69F },
+{ 0xA69E, 0xA69F },
 { 0xA6F0, 0xA6F1 },
 { 0xA802, 0xA802 },
 { 0xA806, 0xA806 },
 { 0xA80B, 0xA80B },
 { 0xA825, 0xA826 },
-{ 0xA8C4, 0xA8C4 },
+{ 0xA8C4, 0xA8C5 },
 { 0xA8E0, 0xA8F1 },
 { 0xA926, 0xA92D },
 { 0xA947, 0xA951 },
@@ -204,7 +205,7 @@ static const struct interval zero_width[] = {
 { 0xABED, 0xABED },
 { 0xFB1E, 0xFB1E },
 { 0xFE00, 0xFE0F },
-{ 0xFE20, 0xFE2D },
+{ 0xFE20, 0xFE2F },
 { 0xFEFF, 0xFEFF },
 { 0xFFF9, 0xFFFB },
 { 0x101FD, 0x101FD },
@@ -228,16 +229,21 @@ static const struct interval zero_width[] = {
 { 0x11173, 0x11173 },
 { 0x11180, 0x11181 },
 { 0x111B6, 0x111BE },
+{ 0x111CA, 0x111CC },
 { 0x1122F, 0x11231 },
 { 0x11234, 0x11234 },
 { 0x11236, 0x11237 },
+{ 0x1123E, 0x1123E },
 { 0x112DF, 0x112DF },
 { 0x112E3, 0x112EA },
-{ 0x11301, 0x11301 },
+{ 0x11300, 0x11301 },
 { 0x1133C, 0x1133C },
 { 0x11340, 0x11340 },
 { 0x11366, 0x1136C },
 { 0x11370, 0x11374 },
+{ 0x11438, 0x1143F },
+{ 0x11442, 0x11444 },
+{ 0x11446, 0x11446 },
 { 0x114B3, 0x114B8 },
 { 0x114BA, 0x114BA },
 { 0x114BF, 0x114C0 },
@@ -245,6 +251,7 @@ static const struct interval zero_width[] = {
 { 0x115B2, 0x115B5 },
 { 0x115BC, 0x115BD },
 { 0x115BF, 0x115C0 },
+{ 0x115DC, 0x115DD },
 { 0x11633, 0x1163A },
 { 0x1163D, 0x1163D },
 { 0x1163F, 0x11640 },
@@ -252,6 +259,16 @@ static const struct interval zero_width[] = {
 { 0x116AD, 0x116AD },
 { 0x116B0, 0x116B5 },
 { 0x116B7, 0x116B7 },
+{ 0x1171D, 0x1171F },
+{ 0x11722, 0x11725 },
+{ 0x11727, 0x1172B },
+{ 0x11C30, 0x11C36 },
+{ 0x11C38, 0x11C3D },
+{ 0x11C3F, 0x11C3F },
+{ 0x11C92, 0x11CA7 },
+{ 0x11CAA, 0x11CB0 },
+{ 0x11CB2, 0x11CB3 },
+{ 0x11CB5, 0x11CB6 },
 { 0x16AF0, 0x16AF4 },
 { 0x16B30, 0x16B36 },
 { 0x16F8F, 0x16F92 },
@@ -262,16 +279,28 @@ static const struct interval zero_width[] = {
 { 0x1D185, 0x1D18B },
 { 0x1D1AA, 0x1D1AD },
 { 0x1D242, 0x1D244 },
+{ 0x1DA00, 0x1DA36 },
+{ 0x1DA3B, 0x1DA6C },
+{ 0x1DA75, 0x1DA75 },
+{ 0x1DA84, 0x1DA84 },
+{ 0x1DA9B, 0x1DA9F },
+{ 0x1DAA1, 0x1DAAF },
+{ 0x1E000, 0x1E006 },
+{ 0x1E008, 0x1E018 },
+{ 0x1E01B, 0x1E021 },
+{ 0x1E023, 0x1E024 },
+{ 0x1E026, 0x1E02A },
 { 0x1E8D0, 0x1E8D6 },
+{ 0x1E944, 0x1E94A },
 { 0xE0001, 0xE0001 },
 { 0xE0020, 0xE007F },
 { 0xE0100, 0xE01EF }
 };
 static const struct interval double_width[] = {
-{ /* plane */ 0x0, 0x1C },
-{ /* plane */ 0x1C, 0x21 },
-{ /* plane */ 0x21, 0x22 },
-{ /* plane */ 0x22, 0x23 },
+{ /* plane */ 0x0, 0x3D },
+{ /* plane */ 0x3D, 0x68 },
+{ /* plane */ 0x68, 0x69 },
+{ /* plane */ 0x69, 0x6A },
 { /* plane */ 0x0, 0x0 },
 { /* plane */ 0x0, 0x0 },
 { /* plane */ 0x0, 0x0 },
@@ -286,7 +315,40 @@ static const struct interval double_width[] = {
 { /* plane */ 0x0, 0x0 },
 { /* plane */ 0x0, 0x0 },
 { 0x1100, 0x115F },
+{ 0x231A, 0x231B },
 { 0x2329, 0x232A },
+{ 0x23E9, 0x23EC },
+{ 0x23F0, 0x23F0 },
+{ 0x23F3, 0x23F3 },
+{ 0x25FD, 0x25FE },
+{ 0x2614, 0x2615 },
+{ 0x2648, 0x2653 },
+{ 0x267F, 0x267F },
+{ 0x2693, 0x2693 },
+{ 0x26A1, 0x26A1 },
+{ 0x26AA, 0x26AB },
+{ 0x26BD, 0x26BE },
+{ 0x26C4, 0x26C5 },
+{ 0x26CE, 0x26CE },
+{ 0x26D4, 0x26D4 },
+{ 0x26EA, 0x26EA },
+{ 0x26F2, 0x26F3 },
+{ 0x26F5, 0x26F5 },
+{ 0x26FA, 0x26FA },
+{ 0x26FD, 0x26FD },
+{ 0x2705, 0x2705 },
+{ 0x270A, 0x270B },
+{ 0x2728, 0x2728 },
+{ 0x274C, 0x274C },
+{ 0x274E, 0x274E },
+{ 0x2753, 0x2755 },
+{ 0x2757, 0x2757 },
+{ 0x2795, 0x2797 },
+{ 0x27B0, 0x27B0 },
+{ 0x27BF, 0x27BF },
+{ 0x2B1B, 0x2B1C },
+{ 0x2B50, 0x2B50 },
+{ 0x2B55, 0x2B55 },
 { 0x2E80, 0x2E99 },
 { 0x2E9B, 0x2EF3 },
 { 0x2F00, 0x2FD5 },
@@ -313,11 +375,49 @@ static const struct interval double_width[] = {
 { 0xFE68, 0xFE6B },
 { 0xFF01, 0xFF60 },
 { 0xFFE0, 0xFFE6 },
+{ 0x16FE0, 0x16FE0 },
+{ 0x17000, 0x187EC },
+{ 0x18800, 0x18AF2 },
 { 0x1B000, 0x1B001 },
+{ 0x1F004, 0x1F004 },
+{ 0x1F0CF, 0x1F0CF },
+{ 0x1F18E, 0x1F18E },
+{ 0x1F191, 0x1F19A },
 { 0x1F200, 0x1F202 },
-{ 0x1F210, 0x1F23A },
+{ 0x1F210, 0x1F23B },
 { 0x1F240, 0x1F248 },
 { 0x1F250, 0x1F251 },
+{ 0x1F300, 0x1F320 },
+{ 0x1F32D, 0x1F335 },
+{ 0x1F337, 0x1F37C },
+{ 0x1F37E, 0x1F393 },
+{ 0x1F3A0, 0x1F3CA },
+{ 0x1F3CF, 0x1F3D3 },
+{ 0x1F3E0, 0x1F3F0 },
+{ 0x1F3F4, 0x1F3F4 },
+{ 0x1F3F8, 0x1F43E },
+{ 0x1F440, 0x1F440 },
+{ 0x1F442, 0x1F4FC },
+{ 0x1F4FF, 0x1F53D },
+{ 0x1F54B, 0x1F54E },
+{ 0x1F550, 0x1F567 },
+{ 0x1F57A, 0x1F57A },
+{ 0x1F595, 0x1F596 },
+{ 0x1F5A4, 0x1F5A4 },
+{ 0x1F5FB, 0x1F64F },
+{ 0x1F680, 0x1F6C5 },
+{ 0x1F6CC, 0x1F6CC },
+{ 0x1F6D0, 0x1F6D2 },
+{ 0x1F6EB, 0x1F6EC },
+{ 0x1F6F4, 0x1F6F6 },
+{ 0x1F910, 0x1F91E },
+{ 0x1F920, 0x1F927 },
+{ 0x1F930, 0x1F930 },
+{ 0x1F933, 0x1F93E },
+{ 0x1F940, 0x1F94B },
+{ 0x1F950, 0x1F95E },
+{ 0x1F980, 0x1F991 },
+{ 0x1F9C0, 0x1F9C0 },
 { 0x20000, 0x2FFFD },
 { 0x30000, 0x3FFFD }
 };

-- 
2.7.2

Beat Bolli· Dec 3, 2016, 10:35 UTC · re: Beat Bolli · lore

[PATCH 3/3] unicode_width.h: fix the double_width[] table

The function bisearch() in utf8.c does a pure binary search in double_width. It does not care about the 17 plane offsets which unicode/uniset/uniset prepends. Leaving the plane offsets in the table may cause wrong results.

Filter out the plane offsets in the update-unicode.sh and regenerate the table.

Signed-off-by: Beat Bolli <dev+git@drbeat.li>
---
 unicode_width.h   | 17 -----------------
 update_unicode.sh |  2 +-
 2 files changed, 1 insertion(+), 18 deletions(-)

Show changes to 2 files +1 −18

unicode_width.h, update_unicode.sh

diff --git a/unicode_width.h b/unicode_width.h
index 73b5fd6..02207be 100644
--- a/unicode_width.h
+++ b/unicode_width.h
@@ -297,23 +297,6 @@ static const struct interval zero_width[] = {
 { 0xE0100, 0xE01EF }
 };
 static const struct interval double_width[] = {
-{ /* plane */ 0x0, 0x3D },
-{ /* plane */ 0x3D, 0x68 },
-{ /* plane */ 0x68, 0x69 },
-{ /* plane */ 0x69, 0x6A },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
 { 0x1100, 0x115F },
 { 0x231A, 0x231B },
 { 0x2329, 0x232A },
diff --git a/update_unicode.sh b/update_unicode.sh
index 3c84270..4c1ec8d 100755
--- a/update_unicode.sh
+++ b/update_unicode.sh
@@ -30,7 +30,7 @@ fi &&
 		  grep -v plane)
 	};
 	static const struct interval double_width[] = {
-		$(uniset/uniset --32 eaw:F,W)
+		$(uniset/uniset --32 eaw:F,W | grep -v plane)
 	};
 	EOF
 )

-- 
2.7.2

Beat Bolli· Dec 3, 2016, 10:53 UTC · re: Beat Bolli · lore

[PATCH v2 1/3] update-unicode.sh: automatically download newer definition files

Checking just for the unicode data files' existence is not sufficient; we should also download them if a newer version exists on the Unicode consortium's servers. Option -N of wget does this nicely for us.

Cc: Torsten Bögershausen <tboegi@web.de>
Signed-off-by: Beat Bolli <dev+git@drbeat.li>
---
Diff to v1:
  - reword the commit message
  - add Thorsten's Cc:

 update_unicode.sh | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

Show changes to update_unicode.sh +2 −6

diff --git a/update_unicode.sh b/update_unicode.sh
index 27af77c..3c84270 100755
--- a/update_unicode.sh
+++ b/update_unicode.sh
@@ -10,12 +10,8 @@ if ! test -d unicode; then
 	mkdir unicode
 fi &&
 ( cd unicode &&
-	if ! test -f UnicodeData.txt; then
-		wget http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
-	fi &&
-	if ! test -f EastAsianWidth.txt; then
-		wget http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt
-	fi &&
+	wget -N http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt \
+		http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt &&
 	if ! test -d uniset; then
 		git clone https://github.com/depp/uniset.git
 	fi &&

-- 
2.7.2

Beat Bolli· Dec 3, 2016, 10:53 UTC · re: Beat Bolli · lore

[PATCH v2 3/3] unicode_width.h: fix the double_width[] table

Filter out the plane offsets in update-unicode.sh and regenerate the table.

Cc: Torsten Bögershausen <tboegi@web.de>
Signed-off-by: Beat Bolli <dev+git@drbeat.li>
---
Diff to v1:
  - add Thorsten's Cc:

 unicode_width.h   | 17 -----------------
 update_unicode.sh |  2 +-
 2 files changed, 1 insertion(+), 18 deletions(-)

Show changes to 2 files +1 −18

unicode_width.h, update_unicode.sh

diff --git a/unicode_width.h b/unicode_width.h
index 73b5fd6..02207be 100644
--- a/unicode_width.h
+++ b/unicode_width.h
@@ -297,23 +297,6 @@ static const struct interval zero_width[] = {
 { 0xE0100, 0xE01EF }
 };
 static const struct interval double_width[] = {
-{ /* plane */ 0x0, 0x3D },
-{ /* plane */ 0x3D, 0x68 },
-{ /* plane */ 0x68, 0x69 },
-{ /* plane */ 0x69, 0x6A },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
 { 0x1100, 0x115F },
 { 0x231A, 0x231B },
 { 0x2329, 0x232A },
diff --git a/update_unicode.sh b/update_unicode.sh
index 3c84270..4c1ec8d 100755
--- a/update_unicode.sh
+++ b/update_unicode.sh
@@ -30,7 +30,7 @@ fi &&
 		  grep -v plane)
 	};
 	static const struct interval double_width[] = {
-		$(uniset/uniset --32 eaw:F,W)
+		$(uniset/uniset --32 eaw:F,W | grep -v plane)
 	};
 	EOF
 )

-- 
2.7.2

Beat Bolli· Dec 3, 2016, 13:19 UTC · re: Beat Bolli · lore

[PATCH v3 1/3] update-unicode.sh: automatically download newer definition files

Cc: Torsten Bögershausen <tboegi@web.de>
Signed-off-by: Beat Bolli <dev+git@drbeat.li>
---
Diff to v2:
  - reorder the commits: fix all of update-unicode.sh first, then
    regenerate unicode_width.h only once

 update_unicode.sh | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

Show changes to update_unicode.sh +2 −6

diff --git a/update_unicode.sh b/update_unicode.sh
index 27af77c..3c84270 100755
--- a/update_unicode.sh
+++ b/update_unicode.sh
@@ -10,12 +10,8 @@ if ! test -d unicode; then
 	mkdir unicode
 fi &&
 ( cd unicode &&
-	if ! test -f UnicodeData.txt; then
-		wget http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
-	fi &&
-	if ! test -f EastAsianWidth.txt; then
-		wget http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt
-	fi &&
+	wget -N http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt \
+		http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt &&
 	if ! test -d uniset; then
 		git clone https://github.com/depp/uniset.git
 	fi &&

-- 
2.7.2

Beat Bolli· Dec 3, 2016, 13:19 UTC · re: Beat Bolli · lore

[PATCH v3 2/3] update-unicode.sh: strip the plane offsets from the double_width[] table

Filter out the plane offsets in update-unicode.sh.

Cc: Torsten Bögershausen <tboegi@web.de>
Signed-off-by: Beat Bolli <dev+git@drbeat.li>
---
 update_unicode.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Show changes to update_unicode.sh +1 −1

diff --git a/update_unicode.sh b/update_unicode.sh
index 3c84270..4c1ec8d 100755
--- a/update_unicode.sh
+++ b/update_unicode.sh
@@ -30,7 +30,7 @@ fi &&
 		  grep -v plane)
 	};
 	static const struct interval double_width[] = {
-		$(uniset/uniset --32 eaw:F,W)
+		$(uniset/uniset --32 eaw:F,W | grep -v plane)
 	};
 	EOF
 )

-- 
2.7.2

Beat Bolli· Dec 3, 2016, 13:19 UTC · re: Beat Bolli · lore

[PATCH v3 3/3] unicode_width.h: update the tables to Unicode 9.0

Rerunning update-unicode.sh that we fixed in the two previous commits produces these new tables.

Signed-off-by: Beat Bolli <dev+git@drbeat.li>
---
 unicode_width.h | 131 +++++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 107 insertions(+), 24 deletions(-)

Show changes to unicode_width.h +107 −24

diff --git a/unicode_width.h b/unicode_width.h
index 47cdd23..02207be 100644
--- a/unicode_width.h
+++ b/unicode_width.h
@@ -25,7 +25,7 @@ static const struct interval zero_width[] = {
 { 0x0825, 0x0827 },
 { 0x0829, 0x082D },
 { 0x0859, 0x085B },
-{ 0x08E4, 0x0902 },
+{ 0x08D4, 0x0902 },
 { 0x093A, 0x093A },
 { 0x093C, 0x093C },
 { 0x0941, 0x0948 },
@@ -120,6 +120,7 @@ static const struct interval zero_width[] = {
 { 0x17C9, 0x17D3 },
 { 0x17DD, 0x17DD },
 { 0x180B, 0x180E },
+{ 0x1885, 0x1886 },
 { 0x18A9, 0x18A9 },
 { 0x1920, 0x1922 },
 { 0x1927, 0x1928 },
@@ -158,7 +159,7 @@ static const struct interval zero_width[] = {
 { 0x1CF4, 0x1CF4 },
 { 0x1CF8, 0x1CF9 },
 { 0x1DC0, 0x1DF5 },
-{ 0x1DFC, 0x1DFF },
+{ 0x1DFB, 0x1DFF },
 { 0x200B, 0x200F },
 { 0x202A, 0x202E },
 { 0x2060, 0x2064 },
@@ -171,13 +172,13 @@ static const struct interval zero_width[] = {
 { 0x3099, 0x309A },
 { 0xA66F, 0xA672 },
 { 0xA674, 0xA67D },
-{ 0xA69F, 0xA69F },
+{ 0xA69E, 0xA69F },
 { 0xA6F0, 0xA6F1 },
 { 0xA802, 0xA802 },
 { 0xA806, 0xA806 },
 { 0xA80B, 0xA80B },
 { 0xA825, 0xA826 },
-{ 0xA8C4, 0xA8C4 },
+{ 0xA8C4, 0xA8C5 },
 { 0xA8E0, 0xA8F1 },
 { 0xA926, 0xA92D },
 { 0xA947, 0xA951 },
@@ -204,7 +205,7 @@ static const struct interval zero_width[] = {
 { 0xABED, 0xABED },
 { 0xFB1E, 0xFB1E },
 { 0xFE00, 0xFE0F },
-{ 0xFE20, 0xFE2D },
+{ 0xFE20, 0xFE2F },
 { 0xFEFF, 0xFEFF },
 { 0xFFF9, 0xFFFB },
 { 0x101FD, 0x101FD },
@@ -228,16 +229,21 @@ static const struct interval zero_width[] = {
 { 0x11173, 0x11173 },
 { 0x11180, 0x11181 },
 { 0x111B6, 0x111BE },
+{ 0x111CA, 0x111CC },
 { 0x1122F, 0x11231 },
 { 0x11234, 0x11234 },
 { 0x11236, 0x11237 },
+{ 0x1123E, 0x1123E },
 { 0x112DF, 0x112DF },
 { 0x112E3, 0x112EA },
-{ 0x11301, 0x11301 },
+{ 0x11300, 0x11301 },
 { 0x1133C, 0x1133C },
 { 0x11340, 0x11340 },
 { 0x11366, 0x1136C },
 { 0x11370, 0x11374 },
+{ 0x11438, 0x1143F },
+{ 0x11442, 0x11444 },
+{ 0x11446, 0x11446 },
 { 0x114B3, 0x114B8 },
 { 0x114BA, 0x114BA },
 { 0x114BF, 0x114C0 },
@@ -245,6 +251,7 @@ static const struct interval zero_width[] = {
 { 0x115B2, 0x115B5 },
 { 0x115BC, 0x115BD },
 { 0x115BF, 0x115C0 },
+{ 0x115DC, 0x115DD },
 { 0x11633, 0x1163A },
 { 0x1163D, 0x1163D },
 { 0x1163F, 0x11640 },
@@ -252,6 +259,16 @@ static const struct interval zero_width[] = {
 { 0x116AD, 0x116AD },
 { 0x116B0, 0x116B5 },
 { 0x116B7, 0x116B7 },
+{ 0x1171D, 0x1171F },
+{ 0x11722, 0x11725 },
+{ 0x11727, 0x1172B },
+{ 0x11C30, 0x11C36 },
+{ 0x11C38, 0x11C3D },
+{ 0x11C3F, 0x11C3F },
+{ 0x11C92, 0x11CA7 },
+{ 0x11CAA, 0x11CB0 },
+{ 0x11CB2, 0x11CB3 },
+{ 0x11CB5, 0x11CB6 },
 { 0x16AF0, 0x16AF4 },
 { 0x16B30, 0x16B36 },
 { 0x16F8F, 0x16F92 },
@@ -262,31 +279,59 @@ static const struct interval zero_width[] = {
 { 0x1D185, 0x1D18B },
 { 0x1D1AA, 0x1D1AD },
 { 0x1D242, 0x1D244 },
+{ 0x1DA00, 0x1DA36 },
+{ 0x1DA3B, 0x1DA6C },
+{ 0x1DA75, 0x1DA75 },
+{ 0x1DA84, 0x1DA84 },
+{ 0x1DA9B, 0x1DA9F },
+{ 0x1DAA1, 0x1DAAF },
+{ 0x1E000, 0x1E006 },
+{ 0x1E008, 0x1E018 },
+{ 0x1E01B, 0x1E021 },
+{ 0x1E023, 0x1E024 },
+{ 0x1E026, 0x1E02A },
 { 0x1E8D0, 0x1E8D6 },
+{ 0x1E944, 0x1E94A },
 { 0xE0001, 0xE0001 },
 { 0xE0020, 0xE007F },
 { 0xE0100, 0xE01EF }
 };
 static const struct interval double_width[] = {
-{ /* plane */ 0x0, 0x1C },
-{ /* plane */ 0x1C, 0x21 },
-{ /* plane */ 0x21, 0x22 },
-{ /* plane */ 0x22, 0x23 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
 { 0x1100, 0x115F },
+{ 0x231A, 0x231B },
 { 0x2329, 0x232A },
+{ 0x23E9, 0x23EC },
+{ 0x23F0, 0x23F0 },
+{ 0x23F3, 0x23F3 },
+{ 0x25FD, 0x25FE },
+{ 0x2614, 0x2615 },
+{ 0x2648, 0x2653 },
+{ 0x267F, 0x267F },
+{ 0x2693, 0x2693 },
+{ 0x26A1, 0x26A1 },
+{ 0x26AA, 0x26AB },
+{ 0x26BD, 0x26BE },
+{ 0x26C4, 0x26C5 },
+{ 0x26CE, 0x26CE },
+{ 0x26D4, 0x26D4 },
+{ 0x26EA, 0x26EA },
+{ 0x26F2, 0x26F3 },
+{ 0x26F5, 0x26F5 },
+{ 0x26FA, 0x26FA },
+{ 0x26FD, 0x26FD },
+{ 0x2705, 0x2705 },
+{ 0x270A, 0x270B },
+{ 0x2728, 0x2728 },
+{ 0x274C, 0x274C },
+{ 0x274E, 0x274E },
+{ 0x2753, 0x2755 },
+{ 0x2757, 0x2757 },
+{ 0x2795, 0x2797 },
+{ 0x27B0, 0x27B0 },
+{ 0x27BF, 0x27BF },
+{ 0x2B1B, 0x2B1C },
+{ 0x2B50, 0x2B50 },
+{ 0x2B55, 0x2B55 },
 { 0x2E80, 0x2E99 },
 { 0x2E9B, 0x2EF3 },
 { 0x2F00, 0x2FD5 },
@@ -313,11 +358,49 @@ static const struct interval double_width[] = {
 { 0xFE68, 0xFE6B },
 { 0xFF01, 0xFF60 },
 { 0xFFE0, 0xFFE6 },
+{ 0x16FE0, 0x16FE0 },
+{ 0x17000, 0x187EC },
+{ 0x18800, 0x18AF2 },
 { 0x1B000, 0x1B001 },
+{ 0x1F004, 0x1F004 },
+{ 0x1F0CF, 0x1F0CF },
+{ 0x1F18E, 0x1F18E },
+{ 0x1F191, 0x1F19A },
 { 0x1F200, 0x1F202 },
-{ 0x1F210, 0x1F23A },
+{ 0x1F210, 0x1F23B },
 { 0x1F240, 0x1F248 },
 { 0x1F250, 0x1F251 },
+{ 0x1F300, 0x1F320 },
+{ 0x1F32D, 0x1F335 },
+{ 0x1F337, 0x1F37C },
+{ 0x1F37E, 0x1F393 },
+{ 0x1F3A0, 0x1F3CA },
+{ 0x1F3CF, 0x1F3D3 },
+{ 0x1F3E0, 0x1F3F0 },
+{ 0x1F3F4, 0x1F3F4 },
+{ 0x1F3F8, 0x1F43E },
+{ 0x1F440, 0x1F440 },
+{ 0x1F442, 0x1F4FC },
+{ 0x1F4FF, 0x1F53D },
+{ 0x1F54B, 0x1F54E },
+{ 0x1F550, 0x1F567 },
+{ 0x1F57A, 0x1F57A },
+{ 0x1F595, 0x1F596 },
+{ 0x1F5A4, 0x1F5A4 },
+{ 0x1F5FB, 0x1F64F },
+{ 0x1F680, 0x1F6C5 },
+{ 0x1F6CC, 0x1F6CC },
+{ 0x1F6D0, 0x1F6D2 },
+{ 0x1F6EB, 0x1F6EC },
+{ 0x1F6F4, 0x1F6F6 },
+{ 0x1F910, 0x1F91E },
+{ 0x1F920, 0x1F927 },
+{ 0x1F930, 0x1F930 },
+{ 0x1F933, 0x1F93E },
+{ 0x1F940, 0x1F94B },
+{ 0x1F950, 0x1F95E },
+{ 0x1F980, 0x1F991 },
+{ 0x1F9C0, 0x1F9C0 },
 { 0x20000, 0x2FFFD },
 { 0x30000, 0x3FFFD }
 };

-- 
2.7.2

Torsten B��gershausen· Dec 3, 2016, 16:40 UTC · re: Beat Bolli · lore

Re: [PATCH v3 1/3] update-unicode.sh: automatically download newer definition files

On Sat, Dec 03, 2016 at 02:19:31PM +0100, Beat Bolli wrote:

Show 5 quoted lines

> Checking just for the unicode data files' existence is not sufficient;
> we should also download them if a newer version exists on the Unicode
> consortium's servers. Option -N of wget does this nicely for us.
> 
> Cc: Torsten B??gershausen <tboegi@web.de>

The V3 series makes perfect sense, thanks for cleaning up my mess. (And can we remove the Cc: line, or replace with it Reviewed-by ?)

Beat Bolli· Dec 3, 2016, 16:41 UTC · re: Torsten B��gershausen · lore

Re: [PATCH v3 1/3] update-unicode.sh: automatically download newer definition files

On 03.12.16 17:40, Torsten =?unknown-8bit?Q?B=C3=B6gershausen?= wrote:

Show 8 quoted lines

> On Sat, Dec 03, 2016 at 02:19:31PM +0100, Beat Bolli wrote:
>> Checking just for the unicode data files' existence is not sufficient;
>> we should also download them if a newer version exists on the Unicode
>> consortium's servers. Option -N of wget does this nicely for us.
>>
>> Cc: Torsten B??gershausen <tboegi@web.de>
> 
> The V3 series makes perfect sense, thanks for cleaning up my mess.

Yeah, it took me three tries, too :-)

> (And can we remove the Cc: line, or replace with it Reviewed-by ?)

If you prefer, sure.

Do you have any other comments?

Beat

Beat Bolli· Dec 3, 2016, 21:00 UTC · re: Beat Bolli · lore

[PATCH v4 1/3] update-unicode.sh: automatically download newer definition files

Reviewed-by: Torsten Boegershausen <tboegi@web.de>
Signed-off-by: Beat Bolli <dev+git@drbeat.li>
---
Diff to v3:
  - change the Cc: into Reviewed-by: on Thorsten's request
  - include the old reroll diffs

Diff to v2:
  - reorder the commits: fix all of update-unicode.sh first, then
    regenerate unicode_width.h only once

Diff to v1:
  - reword the commit message
  - add Thorsten's Cc:

 update_unicode.sh | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

Show changes to update_unicode.sh +2 −6

diff --git a/update_unicode.sh b/update_unicode.sh
index 27af77c..3c84270 100755
--- a/update_unicode.sh
+++ b/update_unicode.sh
@@ -10,12 +10,8 @@ if ! test -d unicode; then
 	mkdir unicode
 fi &&
 ( cd unicode &&
-	if ! test -f UnicodeData.txt; then
-		wget http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
-	fi &&
-	if ! test -f EastAsianWidth.txt; then
-		wget http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt
-	fi &&
+	wget -N http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt \
+		http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt &&
 	if ! test -d uniset; then
 		git clone https://github.com/depp/uniset.git
 	fi &&

-- 
2.7.2

Beat Bolli· Dec 3, 2016, 21:00 UTC · re: Beat Bolli · lore

[PATCH v4 2/3] update-unicode.sh: strip the plane offsets from the double_width[] table

Filter out the plane offsets in update-unicode.sh.

Reviewed-by: Torsten Bögershausen <tboegi@web.de>
Signed-off-by: Beat Bolli <dev+git@drbeat.li>
---
 update_unicode.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Show changes to update_unicode.sh +1 −1

diff --git a/update_unicode.sh b/update_unicode.sh
index 3c84270..4c1ec8d 100755
--- a/update_unicode.sh
+++ b/update_unicode.sh
@@ -30,7 +30,7 @@ fi &&
 		  grep -v plane)
 	};
 	static const struct interval double_width[] = {
-		$(uniset/uniset --32 eaw:F,W)
+		$(uniset/uniset --32 eaw:F,W | grep -v plane)
 	};
 	EOF
 )

-- 
2.7.2

Beat Bolli· Dec 3, 2016, 21:00 UTC · re: Beat Bolli · lore

[PATCH v4 3/3] unicode_width.h: update the tables to Unicode 9.0

Rerunning update-unicode.sh that we fixed in the two previous commits produces these new tables.

Signed-off-by: Beat Bolli <dev+git@drbeat.li>
---
 unicode_width.h | 131 +++++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 107 insertions(+), 24 deletions(-)

Show changes to unicode_width.h +107 −24

diff --git a/unicode_width.h b/unicode_width.h
index 47cdd23..02207be 100644
--- a/unicode_width.h
+++ b/unicode_width.h
@@ -25,7 +25,7 @@ static const struct interval zero_width[] = {
 { 0x0825, 0x0827 },
 { 0x0829, 0x082D },
 { 0x0859, 0x085B },
-{ 0x08E4, 0x0902 },
+{ 0x08D4, 0x0902 },
 { 0x093A, 0x093A },
 { 0x093C, 0x093C },
 { 0x0941, 0x0948 },
@@ -120,6 +120,7 @@ static const struct interval zero_width[] = {
 { 0x17C9, 0x17D3 },
 { 0x17DD, 0x17DD },
 { 0x180B, 0x180E },
+{ 0x1885, 0x1886 },
 { 0x18A9, 0x18A9 },
 { 0x1920, 0x1922 },
 { 0x1927, 0x1928 },
@@ -158,7 +159,7 @@ static const struct interval zero_width[] = {
 { 0x1CF4, 0x1CF4 },
 { 0x1CF8, 0x1CF9 },
 { 0x1DC0, 0x1DF5 },
-{ 0x1DFC, 0x1DFF },
+{ 0x1DFB, 0x1DFF },
 { 0x200B, 0x200F },
 { 0x202A, 0x202E },
 { 0x2060, 0x2064 },
@@ -171,13 +172,13 @@ static const struct interval zero_width[] = {
 { 0x3099, 0x309A },
 { 0xA66F, 0xA672 },
 { 0xA674, 0xA67D },
-{ 0xA69F, 0xA69F },
+{ 0xA69E, 0xA69F },
 { 0xA6F0, 0xA6F1 },
 { 0xA802, 0xA802 },
 { 0xA806, 0xA806 },
 { 0xA80B, 0xA80B },
 { 0xA825, 0xA826 },
-{ 0xA8C4, 0xA8C4 },
+{ 0xA8C4, 0xA8C5 },
 { 0xA8E0, 0xA8F1 },
 { 0xA926, 0xA92D },
 { 0xA947, 0xA951 },
@@ -204,7 +205,7 @@ static const struct interval zero_width[] = {
 { 0xABED, 0xABED },
 { 0xFB1E, 0xFB1E },
 { 0xFE00, 0xFE0F },
-{ 0xFE20, 0xFE2D },
+{ 0xFE20, 0xFE2F },
 { 0xFEFF, 0xFEFF },
 { 0xFFF9, 0xFFFB },
 { 0x101FD, 0x101FD },
@@ -228,16 +229,21 @@ static const struct interval zero_width[] = {
 { 0x11173, 0x11173 },
 { 0x11180, 0x11181 },
 { 0x111B6, 0x111BE },
+{ 0x111CA, 0x111CC },
 { 0x1122F, 0x11231 },
 { 0x11234, 0x11234 },
 { 0x11236, 0x11237 },
+{ 0x1123E, 0x1123E },
 { 0x112DF, 0x112DF },
 { 0x112E3, 0x112EA },
-{ 0x11301, 0x11301 },
+{ 0x11300, 0x11301 },
 { 0x1133C, 0x1133C },
 { 0x11340, 0x11340 },
 { 0x11366, 0x1136C },
 { 0x11370, 0x11374 },
+{ 0x11438, 0x1143F },
+{ 0x11442, 0x11444 },
+{ 0x11446, 0x11446 },
 { 0x114B3, 0x114B8 },
 { 0x114BA, 0x114BA },
 { 0x114BF, 0x114C0 },
@@ -245,6 +251,7 @@ static const struct interval zero_width[] = {
 { 0x115B2, 0x115B5 },
 { 0x115BC, 0x115BD },
 { 0x115BF, 0x115C0 },
+{ 0x115DC, 0x115DD },
 { 0x11633, 0x1163A },
 { 0x1163D, 0x1163D },
 { 0x1163F, 0x11640 },
@@ -252,6 +259,16 @@ static const struct interval zero_width[] = {
 { 0x116AD, 0x116AD },
 { 0x116B0, 0x116B5 },
 { 0x116B7, 0x116B7 },
+{ 0x1171D, 0x1171F },
+{ 0x11722, 0x11725 },
+{ 0x11727, 0x1172B },
+{ 0x11C30, 0x11C36 },
+{ 0x11C38, 0x11C3D },
+{ 0x11C3F, 0x11C3F },
+{ 0x11C92, 0x11CA7 },
+{ 0x11CAA, 0x11CB0 },
+{ 0x11CB2, 0x11CB3 },
+{ 0x11CB5, 0x11CB6 },
 { 0x16AF0, 0x16AF4 },
 { 0x16B30, 0x16B36 },
 { 0x16F8F, 0x16F92 },
@@ -262,31 +279,59 @@ static const struct interval zero_width[] = {
 { 0x1D185, 0x1D18B },
 { 0x1D1AA, 0x1D1AD },
 { 0x1D242, 0x1D244 },
+{ 0x1DA00, 0x1DA36 },
+{ 0x1DA3B, 0x1DA6C },
+{ 0x1DA75, 0x1DA75 },
+{ 0x1DA84, 0x1DA84 },
+{ 0x1DA9B, 0x1DA9F },
+{ 0x1DAA1, 0x1DAAF },
+{ 0x1E000, 0x1E006 },
+{ 0x1E008, 0x1E018 },
+{ 0x1E01B, 0x1E021 },
+{ 0x1E023, 0x1E024 },
+{ 0x1E026, 0x1E02A },
 { 0x1E8D0, 0x1E8D6 },
+{ 0x1E944, 0x1E94A },
 { 0xE0001, 0xE0001 },
 { 0xE0020, 0xE007F },
 { 0xE0100, 0xE01EF }
 };
 static const struct interval double_width[] = {
-{ /* plane */ 0x0, 0x1C },
-{ /* plane */ 0x1C, 0x21 },
-{ /* plane */ 0x21, 0x22 },
-{ /* plane */ 0x22, 0x23 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
-{ /* plane */ 0x0, 0x0 },
 { 0x1100, 0x115F },
+{ 0x231A, 0x231B },
 { 0x2329, 0x232A },
+{ 0x23E9, 0x23EC },
+{ 0x23F0, 0x23F0 },
+{ 0x23F3, 0x23F3 },
+{ 0x25FD, 0x25FE },
+{ 0x2614, 0x2615 },
+{ 0x2648, 0x2653 },
+{ 0x267F, 0x267F },
+{ 0x2693, 0x2693 },
+{ 0x26A1, 0x26A1 },
+{ 0x26AA, 0x26AB },
+{ 0x26BD, 0x26BE },
+{ 0x26C4, 0x26C5 },
+{ 0x26CE, 0x26CE },
+{ 0x26D4, 0x26D4 },
+{ 0x26EA, 0x26EA },
+{ 0x26F2, 0x26F3 },
+{ 0x26F5, 0x26F5 },
+{ 0x26FA, 0x26FA },
+{ 0x26FD, 0x26FD },
+{ 0x2705, 0x2705 },
+{ 0x270A, 0x270B },
+{ 0x2728, 0x2728 },
+{ 0x274C, 0x274C },
+{ 0x274E, 0x274E },
+{ 0x2753, 0x2755 },
+{ 0x2757, 0x2757 },
+{ 0x2795, 0x2797 },
+{ 0x27B0, 0x27B0 },
+{ 0x27BF, 0x27BF },
+{ 0x2B1B, 0x2B1C },
+{ 0x2B50, 0x2B50 },
+{ 0x2B55, 0x2B55 },
 { 0x2E80, 0x2E99 },
 { 0x2E9B, 0x2EF3 },
 { 0x2F00, 0x2FD5 },
@@ -313,11 +358,49 @@ static const struct interval double_width[] = {
 { 0xFE68, 0xFE6B },
 { 0xFF01, 0xFF60 },
 { 0xFFE0, 0xFFE6 },
+{ 0x16FE0, 0x16FE0 },
+{ 0x17000, 0x187EC },
+{ 0x18800, 0x18AF2 },
 { 0x1B000, 0x1B001 },
+{ 0x1F004, 0x1F004 },
+{ 0x1F0CF, 0x1F0CF },
+{ 0x1F18E, 0x1F18E },
+{ 0x1F191, 0x1F19A },
 { 0x1F200, 0x1F202 },
-{ 0x1F210, 0x1F23A },
+{ 0x1F210, 0x1F23B },
 { 0x1F240, 0x1F248 },
 { 0x1F250, 0x1F251 },
+{ 0x1F300, 0x1F320 },
+{ 0x1F32D, 0x1F335 },
+{ 0x1F337, 0x1F37C },
+{ 0x1F37E, 0x1F393 },
+{ 0x1F3A0, 0x1F3CA },
+{ 0x1F3CF, 0x1F3D3 },
+{ 0x1F3E0, 0x1F3F0 },
+{ 0x1F3F4, 0x1F3F4 },
+{ 0x1F3F8, 0x1F43E },
+{ 0x1F440, 0x1F440 },
+{ 0x1F442, 0x1F4FC },
+{ 0x1F4FF, 0x1F53D },
+{ 0x1F54B, 0x1F54E },
+{ 0x1F550, 0x1F567 },
+{ 0x1F57A, 0x1F57A },
+{ 0x1F595, 0x1F596 },
+{ 0x1F5A4, 0x1F5A4 },
+{ 0x1F5FB, 0x1F64F },
+{ 0x1F680, 0x1F6C5 },
+{ 0x1F6CC, 0x1F6CC },
+{ 0x1F6D0, 0x1F6D2 },
+{ 0x1F6EB, 0x1F6EC },
+{ 0x1F6F4, 0x1F6F6 },
+{ 0x1F910, 0x1F91E },
+{ 0x1F920, 0x1F927 },
+{ 0x1F930, 0x1F930 },
+{ 0x1F933, 0x1F93E },
+{ 0x1F940, 0x1F94B },
+{ 0x1F950, 0x1F95E },
+{ 0x1F980, 0x1F991 },
+{ 0x1F9C0, 0x1F9C0 },
 { 0x20000, 0x2FFFD },
 { 0x30000, 0x3FFFD }
 };

-- 
2.7.2

Torsten Bögershausen· Dec 4, 2016, 07:58 UTC · re: Beat Bolli · lore

Re: [PATCH v4 1/3] update-unicode.sh: automatically download newer definition files

On Sat, Dec 03, 2016 at 10:00:47PM +0100, Beat Bolli wrote:

Show 5 quoted lines

> Checking just for the unicode data files' existence is not sufficient;
> we should also download them if a newer version exists on the Unicode
> consortium's servers. Option -N of wget does this nicely for us.
> 
> Reviewed-by: Torsten Boegershausen <tboegi@web.de>

Minor remark (Not sure if this motivates v5, may be Junio can fix it locally?) s/oe/ö/

Beside this: Thanks again (and I learned about the -N option of wget)

Junio C Hamano· Dec 5, 2016, 20:31 UTC · re: Torsten Bögershausen · lore

Re: [PATCH v4 1/3] update-unicode.sh: automatically download newer definition files

Torsten Bögershausen <tboegi@web.de> writes:

Show 11 quoted lines

> On Sat, Dec 03, 2016 at 10:00:47PM +0100, Beat Bolli wrote:
>> Checking just for the unicode data files' existence is not sufficient;
>> we should also download them if a newer version exists on the Unicode
>> consortium's servers. Option -N of wget does this nicely for us.
>> 
>> Reviewed-by: Torsten Boegershausen <tboegi@web.de>
>
> Minor remark (Not sure if this motivates v5, may be Junio can fix it locally?)
> s/oe/ö/
>
> Beside this: Thanks again (and I learned about the -N option of wget)

Will fix up while queuing (only 1/3 needs it, 2/3 has it right).

Also, I'll do s/update-unicode.sh/update_unicode.sh/ on the title and the message to match the reality. At some point we might want to fix the reality to match people's expectations, though.

Thanks.

Beat Bolli· Dec 7, 2016, 00:17 UTC · re: Junio C Hamano · lore

Re: [PATCH v4 1/3] update-unicode.sh: automatically download newer definition files

On 05.12.16 21:31, Junio C Hamano wrote:

Show 19 quoted lines

> Torsten Bögershausen <tboegi@web.de> writes:
> 
>> On Sat, Dec 03, 2016 at 10:00:47PM +0100, Beat Bolli wrote:
>>> Checking just for the unicode data files' existence is not sufficient;
>>> we should also download them if a newer version exists on the Unicode
>>> consortium's servers. Option -N of wget does this nicely for us.
>>>
>>> Reviewed-by: Torsten Boegershausen <tboegi@web.de>
>>
>> Minor remark (Not sure if this motivates v5, may be Junio can fix it locally?)
>> s/oe/ö/
>>
>> Beside this: Thanks again (and I learned about the -N option of wget)
> 
> Will fix up while queuing (only 1/3 needs it, 2/3 has it right).
> 
> Also, I'll do s/update-unicode.sh/update_unicode.sh/ on the title
> and the message to match the reality.  At some point we might want
> to fix the reality to match people's expectations, though.

Thanks, Junio. This was a bit sloppy of me.

I really appreciate your regard for the small things!

Cheers, Beat

jbh· Dec 7, 2016, 01:00 UTC · re: Beat Bolli · lore

unsubscribe

Beat Bolli· Dec 3, 2016, 10:53 UTC · re: Beat Bolli · lore

[PATCH v2 2/3] unicode_width.h: update the tables to Unicode 9.0

Rerunning update-unicode.sh fixed in the previous commit produces these new tables.

Signed-off-by: Beat Bolli <dev+git@drbeat.li>
---
Diff to v1:
  - reword the commit message

 unicode_width.h | 122 +++++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 111 insertions(+), 11 deletions(-)

Show changes to unicode_width.h +111 −11

diff --git a/unicode_width.h b/unicode_width.h
index 47cdd23..73b5fd6 100644
--- a/unicode_width.h
+++ b/unicode_width.h
@@ -25,7 +25,7 @@ static const struct interval zero_width[] = {
 { 0x0825, 0x0827 },
 { 0x0829, 0x082D },
 { 0x0859, 0x085B },
-{ 0x08E4, 0x0902 },
+{ 0x08D4, 0x0902 },
 { 0x093A, 0x093A },
 { 0x093C, 0x093C },
 { 0x0941, 0x0948 },
@@ -120,6 +120,7 @@ static const struct interval zero_width[] = {
 { 0x17C9, 0x17D3 },
 { 0x17DD, 0x17DD },
 { 0x180B, 0x180E },
+{ 0x1885, 0x1886 },
 { 0x18A9, 0x18A9 },
 { 0x1920, 0x1922 },
 { 0x1927, 0x1928 },
@@ -158,7 +159,7 @@ static const struct interval zero_width[] = {
 { 0x1CF4, 0x1CF4 },
 { 0x1CF8, 0x1CF9 },
 { 0x1DC0, 0x1DF5 },
-{ 0x1DFC, 0x1DFF },
+{ 0x1DFB, 0x1DFF },
 { 0x200B, 0x200F },
 { 0x202A, 0x202E },
 { 0x2060, 0x2064 },
@@ -171,13 +172,13 @@ static const struct interval zero_width[] = {
 { 0x3099, 0x309A },
 { 0xA66F, 0xA672 },
 { 0xA674, 0xA67D },
-{ 0xA69F, 0xA69F },
+{ 0xA69E, 0xA69F },
 { 0xA6F0, 0xA6F1 },
 { 0xA802, 0xA802 },
 { 0xA806, 0xA806 },
 { 0xA80B, 0xA80B },
 { 0xA825, 0xA826 },
-{ 0xA8C4, 0xA8C4 },
+{ 0xA8C4, 0xA8C5 },
 { 0xA8E0, 0xA8F1 },
 { 0xA926, 0xA92D },
 { 0xA947, 0xA951 },
@@ -204,7 +205,7 @@ static const struct interval zero_width[] = {
 { 0xABED, 0xABED },
 { 0xFB1E, 0xFB1E },
 { 0xFE00, 0xFE0F },
-{ 0xFE20, 0xFE2D },
+{ 0xFE20, 0xFE2F },
 { 0xFEFF, 0xFEFF },
 { 0xFFF9, 0xFFFB },
 { 0x101FD, 0x101FD },
@@ -228,16 +229,21 @@ static const struct interval zero_width[] = {
 { 0x11173, 0x11173 },
 { 0x11180, 0x11181 },
 { 0x111B6, 0x111BE },
+{ 0x111CA, 0x111CC },
 { 0x1122F, 0x11231 },
 { 0x11234, 0x11234 },
 { 0x11236, 0x11237 },
+{ 0x1123E, 0x1123E },
 { 0x112DF, 0x112DF },
 { 0x112E3, 0x112EA },
-{ 0x11301, 0x11301 },
+{ 0x11300, 0x11301 },
 { 0x1133C, 0x1133C },
 { 0x11340, 0x11340 },
 { 0x11366, 0x1136C },
 { 0x11370, 0x11374 },
+{ 0x11438, 0x1143F },
+{ 0x11442, 0x11444 },
+{ 0x11446, 0x11446 },
 { 0x114B3, 0x114B8 },
 { 0x114BA, 0x114BA },
 { 0x114BF, 0x114C0 },
@@ -245,6 +251,7 @@ static const struct interval zero_width[] = {
 { 0x115B2, 0x115B5 },
 { 0x115BC, 0x115BD },
 { 0x115BF, 0x115C0 },
+{ 0x115DC, 0x115DD },
 { 0x11633, 0x1163A },
 { 0x1163D, 0x1163D },
 { 0x1163F, 0x11640 },
@@ -252,6 +259,16 @@ static const struct interval zero_width[] = {
 { 0x116AD, 0x116AD },
 { 0x116B0, 0x116B5 },
 { 0x116B7, 0x116B7 },
+{ 0x1171D, 0x1171F },
+{ 0x11722, 0x11725 },
+{ 0x11727, 0x1172B },
+{ 0x11C30, 0x11C36 },
+{ 0x11C38, 0x11C3D },
+{ 0x11C3F, 0x11C3F },
+{ 0x11C92, 0x11CA7 },
+{ 0x11CAA, 0x11CB0 },
+{ 0x11CB2, 0x11CB3 },
+{ 0x11CB5, 0x11CB6 },
 { 0x16AF0, 0x16AF4 },
 { 0x16B30, 0x16B36 },
 { 0x16F8F, 0x16F92 },
@@ -262,16 +279,28 @@ static const struct interval zero_width[] = {
 { 0x1D185, 0x1D18B },
 { 0x1D1AA, 0x1D1AD },
 { 0x1D242, 0x1D244 },
+{ 0x1DA00, 0x1DA36 },
+{ 0x1DA3B, 0x1DA6C },
+{ 0x1DA75, 0x1DA75 },
+{ 0x1DA84, 0x1DA84 },
+{ 0x1DA9B, 0x1DA9F },
+{ 0x1DAA1, 0x1DAAF },
+{ 0x1E000, 0x1E006 },
+{ 0x1E008, 0x1E018 },
+{ 0x1E01B, 0x1E021 },
+{ 0x1E023, 0x1E024 },
+{ 0x1E026, 0x1E02A },
 { 0x1E8D0, 0x1E8D6 },
+{ 0x1E944, 0x1E94A },
 { 0xE0001, 0xE0001 },
 { 0xE0020, 0xE007F },
 { 0xE0100, 0xE01EF }
 };
 static const struct interval double_width[] = {
-{ /* plane */ 0x0, 0x1C },
-{ /* plane */ 0x1C, 0x21 },
-{ /* plane */ 0x21, 0x22 },
-{ /* plane */ 0x22, 0x23 },
+{ /* plane */ 0x0, 0x3D },
+{ /* plane */ 0x3D, 0x68 },
+{ /* plane */ 0x68, 0x69 },
+{ /* plane */ 0x69, 0x6A },
 { /* plane */ 0x0, 0x0 },
 { /* plane */ 0x0, 0x0 },
 { /* plane */ 0x0, 0x0 },
@@ -286,7 +315,40 @@ static const struct interval double_width[] = {
 { /* plane */ 0x0, 0x0 },
 { /* plane */ 0x0, 0x0 },
 { 0x1100, 0x115F },
+{ 0x231A, 0x231B },
 { 0x2329, 0x232A },
+{ 0x23E9, 0x23EC },
+{ 0x23F0, 0x23F0 },
+{ 0x23F3, 0x23F3 },
+{ 0x25FD, 0x25FE },
+{ 0x2614, 0x2615 },
+{ 0x2648, 0x2653 },
+{ 0x267F, 0x267F },
+{ 0x2693, 0x2693 },
+{ 0x26A1, 0x26A1 },
+{ 0x26AA, 0x26AB },
+{ 0x26BD, 0x26BE },
+{ 0x26C4, 0x26C5 },
+{ 0x26CE, 0x26CE },
+{ 0x26D4, 0x26D4 },
+{ 0x26EA, 0x26EA },
+{ 0x26F2, 0x26F3 },
+{ 0x26F5, 0x26F5 },
+{ 0x26FA, 0x26FA },
+{ 0x26FD, 0x26FD },
+{ 0x2705, 0x2705 },
+{ 0x270A, 0x270B },
+{ 0x2728, 0x2728 },
+{ 0x274C, 0x274C },
+{ 0x274E, 0x274E },
+{ 0x2753, 0x2755 },
+{ 0x2757, 0x2757 },
+{ 0x2795, 0x2797 },
+{ 0x27B0, 0x27B0 },
+{ 0x27BF, 0x27BF },
+{ 0x2B1B, 0x2B1C },
+{ 0x2B50, 0x2B50 },
+{ 0x2B55, 0x2B55 },
 { 0x2E80, 0x2E99 },
 { 0x2E9B, 0x2EF3 },
 { 0x2F00, 0x2FD5 },
@@ -313,11 +375,49 @@ static const struct interval double_width[] = {
 { 0xFE68, 0xFE6B },
 { 0xFF01, 0xFF60 },
 { 0xFFE0, 0xFFE6 },
+{ 0x16FE0, 0x16FE0 },
+{ 0x17000, 0x187EC },
+{ 0x18800, 0x18AF2 },
 { 0x1B000, 0x1B001 },
+{ 0x1F004, 0x1F004 },
+{ 0x1F0CF, 0x1F0CF },
+{ 0x1F18E, 0x1F18E },
+{ 0x1F191, 0x1F19A },
 { 0x1F200, 0x1F202 },
-{ 0x1F210, 0x1F23A },
+{ 0x1F210, 0x1F23B },
 { 0x1F240, 0x1F248 },
 { 0x1F250, 0x1F251 },
+{ 0x1F300, 0x1F320 },
+{ 0x1F32D, 0x1F335 },
+{ 0x1F337, 0x1F37C },
+{ 0x1F37E, 0x1F393 },
+{ 0x1F3A0, 0x1F3CA },
+{ 0x1F3CF, 0x1F3D3 },
+{ 0x1F3E0, 0x1F3F0 },
+{ 0x1F3F4, 0x1F3F4 },
+{ 0x1F3F8, 0x1F43E },
+{ 0x1F440, 0x1F440 },
+{ 0x1F442, 0x1F4FC },
+{ 0x1F4FF, 0x1F53D },
+{ 0x1F54B, 0x1F54E },
+{ 0x1F550, 0x1F567 },
+{ 0x1F57A, 0x1F57A },
+{ 0x1F595, 0x1F596 },
+{ 0x1F5A4, 0x1F5A4 },
+{ 0x1F5FB, 0x1F64F },
+{ 0x1F680, 0x1F6C5 },
+{ 0x1F6CC, 0x1F6CC },
+{ 0x1F6D0, 0x1F6D2 },
+{ 0x1F6EB, 0x1F6EC },
+{ 0x1F6F4, 0x1F6F6 },
+{ 0x1F910, 0x1F91E },
+{ 0x1F920, 0x1F927 },
+{ 0x1F930, 0x1F930 },
+{ 0x1F933, 0x1F93E },
+{ 0x1F940, 0x1F94B },
+{ 0x1F950, 0x1F95E },
+{ 0x1F980, 0x1F991 },
+{ 0x1F9C0, 0x1F9C0 },
 { 0x20000, 0x2FFFD },
 { 0x30000, 0x3FFFD }
 };

-- 
2.7.2