Merge pull request #1606 from sharkdp/syslog

Improve Syslog and general log file highlighting

10 files changed, 224 insertions, 4 deletions

diff --git a/.gitmodules b/.gitmodules
index db5c1b5d..4494055b 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -94,10 +94,6 @@
 [submodule "assets/syntaxes/Assembly (ARM)"]
 	path = assets/syntaxes/02_Extra/Assembly (ARM)
 	url = https://github.com/tvi/Sublime-ARM-Assembly
-[submodule "assets/syntaxes/syslog-syntax"]
-	path = assets/syntaxes/02_Extra/Syslog
-	url = https://github.com/caos21/syslog-syntax.git
-	branch = master
 [submodule "assets/syntaxes/protobuf-syntax-highlighting"]
 	path = assets/syntaxes/02_Extra/Protobuf
 	url = https://github.com/VcamX/protobuf-syntax-highlighting.git
diff --git a/CHANGELOG.md b/CHANGELOG.md
index d3341148..617f19b6 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -13,6 +13,7 @@
 
 ## Syntaxes
 
+- Improved the Syslog syntax highlighting, see #1606 (@keith-hall)
 - Replaced "Advanced CSV" with a custom CSV syntax definition written especially for `bat`; see #1574 (@keith-hall)
 
 ## New themes
diff --git a/assets/patches/Monokai-Extended.tmTheme.patch b/assets/patches/Monokai-Extended.tmTheme.patch
index 16624d5f..106b584d 100644
--- a/assets/patches/Monokai-Extended.tmTheme.patch
+++ b/assets/patches/Monokai-Extended.tmTheme.patch
@@ -16,3 +16,21 @@ index 9c2aa3e..180cbbf 100644
        </dict>
      </dict>
      <dict>
+@@ -1027,7 +1027,7 @@
+       <key>name</key>
+       <string>Invalid</string>
+       <key>scope</key>
+-      <string>invalid</string>
++      <string>invalid, markup.error</string>
+       <key>settings</key>
+       <dict>
+         <key>background</key>
+@@ -1042,7 +1042,7 @@
+       <key>name</key>
+       <string>Invalid deprecated</string>
+       <key>scope</key>
+-      <string>invalid.deprecated</string>
++      <string>invalid.deprecated, markup.warning</string>
+       <key>settings</key>
+       <dict>
+         <key>background</key>
diff --git a/assets/syntaxes/02_Extra/Syslog b/assets/syntaxes/02_Extra/Syslog
deleted file mode 160000
-Subproject 7628d4e0b89d3b4f0dcc014bfb4a3e3433f5133
diff --git a/assets/syntaxes/02_Extra/log.sublime-syntax b/assets/syntaxes/02_Extra/log.sublime-syntax
new file mode 100644
index 00000000..3c699d2e
--- /dev/null
+++ b/assets/syntaxes/02_Extra/log.sublime-syntax
@@ -0,0 +1,116 @@
+%YAML 1.2
+---
+# See http://www.sublimetext.com/docs/3/syntax.html
+file_extensions:
+  - log
+scope: text.log
+variables:
+  ipv4_part: (?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)
+contexts:
+  main:
+    - match: (\w+)(=)
+      captures:
+        1: variable.parameter.log
+        2: keyword.operator.assignment.log
+    - match: (')([^']*)(')
+      scope: string.quoted.single.log
+      captures:
+        1: punctuation.definition.string.begin.log
+        3: punctuation.definition.string.end.log
+    - match: (")([^"]*)(")
+      scope: string.quoted.double.log
+      captures:
+        1: punctuation.definition.string.begin.log
+        3: punctuation.definition.string.end.log
+    - include: dates
+    - include: ip_addresses
+    - include: numbers
+    - match: \b(?i:fail(?:ure|ed)?|error|exception)\b
+      scope: markup.error.log
+    - match: \b(?i:warn(?:ing)?)\b
+      scope: markup.warning.log
+    #- include: scope:text.html.markdown#autolink-inet
+    - match: \b\w+:/{2,3}
+      scope: markup.underline.link.scheme.log
+      push: url-host
+  dates:
+    - match: \b\d{4}-\d{2}-\d{2}\b
+      scope: meta.date.log meta.number.integer.decimal.log constant.numeric.value.log
+    - match: \b\d{4}/\d{2}/\d{2}\b
+      scope: meta.date.log meta.number.integer.decimal.log constant.numeric.value.log
+    - match: \b(?:[01]\d|2[0-3]):(?:[0-5]\d):(?:[0-5]\d)(?:(\.)\d{3})?\b
+      scope: meta.time.log meta.number.integer.decimal.log constant.numeric.value.log
+      captures:
+        1: punctuation.separator.decimal.log
+  ip_addresses:
+    - match: \b(?=(?:{{ipv4_part}}\.){3}{{ipv4_part}}\b)
+      push:
+        - meta_scope: meta.ipaddress.v4.log meta.number.integer.decimal.log
+        - match: \d+
+          scope: constant.numeric.value.log
+        - match: \.
+          scope: punctuation.separator.sequence.log
+        - match: ''
+          pop: true
+    - match: (?=(?:\h{0,4}:){2,6}\h{1,4}\b)
+      push:
+        - meta_scope: meta.ipaddress.v6.log meta.number.integer.hexadecimal.log
+        - match: \h{1,4}
+          scope: constant.numeric.value.log
+        - match: ':'
+          scope: punctuation.separator.sequence.log
+        - match: ''
+          pop: true
+  numbers:
+    - match: \b(0x)(\h+)(?:(\.)(\h+))?\b
+      scope: meta.number.float.hexadecimal.log
+      captures:
+        1: constant.numeric.base.log
+        2: constant.numeric.value.log
+        3: constant.numeric.value.log punctuation.separator.decimal.log
+        4: constant.numeric.value.log
+    - match: \b\d+(\.)\d+\b
+      scope: meta.number.float.log constant.numeric.value.log
+      captures:
+        1: punctuation.separator.decimal.log
+    - match: \b\d+\b
+      scope: meta.number.integer.log constant.numeric.value.log
+  url-host:
+    - meta_content_scope: markup.underline.link.host.log
+    - match: \[
+      scope: punctuation.section.brackets.begin.log
+      push:
+        - match: \]
+          scope: punctuation.section.brackets.end.log
+          pop: true
+        - include: ip_addresses
+    - match: '[^:/\s]+'
+    - match: ''
+      set: url-after-host
+  url-after-host:
+    - match: (:)(\d+)
+      scope: markup.underline.link.port.log
+      captures:
+        1: punctuation.separator.mapping.port.log
+        2: constant.numeric.value.log
+    #- include: scope:text.html.markdown#url-escaped-chars
+    - match: (%)\h{2}
+      scope: markup.underline.link.path.log constant.character.escape.url.log
+      captures:
+        1: punctuation.definition.escape.log
+    # After a valid domain, zero or more non-space non-< characters may follow
+    - match: (?=[?!.,:*_~]*[\s<]) # Trailing punctuation (specifically, ?, !, ., ,, :, *, _, and ~) will not be considered part of the autolink, though they may be included in the interior of the link
+      pop: true
+    - match: \( # When an autolink ends in ), we scan the entire autolink for the total number of parentheses. If there is a greater number of closing parentheses than opening ones, we don’t consider the last character part of the autolink, in order to facilitate including an autolink inside a parenthesis
+      push:
+        - meta_scope: markup.underline.link.path.log
+        - match: (?=[?!.,:*_~]*[\s<])
+          pop: true
+        - match: \)
+          pop: true
+    - match: (?=\)[?!.,:*_~]*[\s<])
+      pop: true
+    - match: '[^?!.,:*_~\s<&()%]+|\S'
+      scope: markup.underline.link.path.log
+    - match: ''
+      pop: true
diff --git a/assets/syntaxes/02_Extra/syslog.sublime-syntax b/assets/syntaxes/02_Extra/syslog.sublime-syntax
new file mode 100644
index 00000000..ce782e50
--- /dev/null
+++ b/assets/syntaxes/02_Extra/syslog.sublime-syntax
@@ -0,0 +1,63 @@
+%YAML 1.2
+---
+# http://www.sublimetext.com/docs/3/syntax.html
+name: syslog
+file_extensions:
+  - syslog
+scope: text.log.syslog
+contexts:
+  main:
+    - match: ^(\w+\s+\d+)\s+(\d{2}:\d{2}:\d{2})
+      scope: meta.datetime.syslog constant.numeric.syslog
+      captures:
+        1: meta.date.syslog
+        2: meta.time.syslog
+      push: loghost
+    - match: ^
+      push: text
+  loghost:
+    - match: '[\w-]+'
+      scope: entity.other.attribute-name.loghost.syslog
+      set: process
+  process:
+    - match: ([\w-]+)(?:(\[)(\d+)(\]))?(:)
+      captures:
+        1: support.function.process.syslog
+        2: punctuation.separator.pid.begin.syslog
+        3: meta.pid.syslog meta.number.integer.syslog constant.numeric.value.syslog
+        4: punctuation.separator.pid.end.syslog
+        5: punctuation.separator.mapping.syslog
+      set: structured-data
+  structured-data:
+    - match: '\['
+      scope: punctuation.section.mapping.begin.syslog
+      push:
+        - match: \]
+          scope: punctuation.section.mapping.end.syslog
+          pop: true
+        - match: \w+
+          scope: variable.parameter.syslog
+        - match: =
+          scope: keyword.operator.assignment.syslog
+          push:
+            - match: '[^\s\]]+'
+              scope: constant.other.syslog
+              pop: true
+            - match: (?=\])
+              pop: true
+    - match: (?=\S)
+      set: text
+  text:
+    - match: $
+      pop: true
+    - match: '<\w+>'
+      scope: constant.language.syslog
+    - match: \b(CMD)\b\s+(\()
+      captures:
+        1: entity.name.label.syslog
+        2: punctuation.section.block.begin.syslog
+      embed: scope:source.shell.bash
+      escape: \)$
+      escape_captures:
+        0: punctuation.section.block.end.syslog
+    - include: scope:text.log
diff --git a/tests/syntax-tests/highlighted/Log/example.log b/tests/syntax-tests/highlighted/Log/example.log
new file mode 100644
index 00000000..8387670c
--- /dev/null
+++ b/tests/syntax-tests/highlighted/Log/example.log
@@ -0,0 +1,2 @@
+2021-03-06 23:22:21.392 https://[2001:db8:4006:812::200e]:8080/path/the%20page.html
+2021-03-06 23:22:21 https://example.com:8080/path/the%20page(with_parens).html
diff --git a/tests/syntax-tests/highlighted/Syslog/example.syslog b/tests/syntax-tests/highlighted/Syslog/example.syslog
new file mode 100644
index 00000000..35002a83
--- /dev/null
+++ b/tests/syntax-tests/highlighted/Syslog/example.syslog
@@ -0,0 +1,11 @@
+Apr  4 00:00:01 hostname-here systemd[1]: logrotate.service: Succeeded.
+Apr  4 00:00:01 hostname-here systemd[1]: Finished Rotate log files.
+Apr  4 00:00:01 hostname-here colord[920]: failed to get session [pid 137485]: No data available
+Apr  4 00:00:21 hostname-here kernel: [55604.908232] audit: type=1400 audit(1617483621.094:28): apparmor="DENIED" operation="capable" profile="/usr/sbin/cups-browsed" pid=59311 comm="cups-browsed" capability=23  capname="sys_nice"
+Apr  4 00:01:38 hostname-here systemd-resolved[721]: Server returned error NXDOMAIN, mitigating potential DNS violation DVE-2018-0001, retrying transaction with reduced feature level UDP.
+Apr  4 00:04:46 hostname-here ntpd[952]: Soliciting pool server 255.76.59.37
+Apr  4 00:05:21 hostname-here ntpd[952]: ::1 local addr 0:0:0:0:0:0:0:1 -> <null>
+Apr  4 00:06:29 hostname-here ntpd[952]: receive: Unexpected origin timestamp 0xe414a8d1.82e825f5 does not match aorg 0xe414a8d5.82c50d8c from server@127.0.0.1 xmt 0xe414a8d1.e671d7c4
+Apr  4 09:30:01 hostname-here CRON[89278]: (root) CMD ([ -x /etc/init.d/anacron ] && if [ ! -d /run/systemd/system ]; then /usr/sbin/invoke-rc.d anacron start >/dev/null; fi)
+Apr  4 16:32:07 hostname-here NetworkManager[740]: <info>  [1617629527.1101] manager: NetworkManager state is now CONNECTED_GLOBAL
+Apr  4 22:00:45 hostname-here dbus-daemon[1094]: [session uid=1000 pid=1094] Successfully activated service 'io.github.celluloid_player.Celluloid'
diff --git a/tests/syntax-tests/source/Log/example.log b/tests/syntax-tests/source/Log/example.log
new file mode 100644
index 00000000..35eb1c78
--- /dev/null
+++ b/tests/syntax-tests/source/Log/example.log
@@ -0,0 +1,2 @@
+2021-03-06 23:22:21.392 https://[2001:db8:4006:812::200e]:8080/path/the%20page.html
+2021-03-06 23:22:21 https://example.com:8080/path/the%20page(with_parens).html
diff --git a/tests/syntax-tests/source/Syslog/example.syslog b/tests/syntax-tests/source/Syslog/example.syslog
new file mode 100644
index 00000000..337f1434
--- /dev/null
+++ b/tests/syntax-tests/source/Syslog/example.syslog
@@ -0,0 +1,11 @@
+Apr  4 00:00:01 hostname-here systemd[1]: logrotate.service: Succeeded.
+Apr  4 00:00:01 hostname-here systemd[1]: Finished Rotate log files.
+Apr  4 00:00:01 hostname-here colord[920]: failed to get session [pid 137485]: No data available
+Apr  4 00:00:21 hostname-here kernel: [55604.908232] audit: type=1400 audit(1617483621.094:28): apparmor="DENIED" operation="capable" profile="/usr/sbin/cups-browsed" pid=59311 comm="cups-browsed" capability=23  capname="sys_nice"
+Apr  4 00:01:38 hostname-here systemd-resolved[721]: Server returned error NXDOMAIN, mitigating potential DNS violation DVE-2018-0001, retrying transaction with reduced feature level UDP.
+Apr  4 00:04:46 hostname-here ntpd[952]: Soliciting pool server 255.76.59.37
+Apr  4 00:05:21 hostname-here ntpd[952]: ::1 local addr 0:0:0:0:0:0:0:1 -> <null>
+Apr  4 00:06:29 hostname-here ntpd[952]: receive: Unexpected origin timestamp 0xe414a8d1.82e825f5 does not match aorg 0xe414a8d5.82c50d8c from server@127.0.0.1 xmt 0xe414a8d1.e671d7c4
+Apr  4 09:30:01 hostname-here CRON[89278]: (root) CMD ([ -x /etc/init.d/anacron ] && if [ ! -d /run/systemd/system ]; then /usr/sbin/invoke-rc.d anacron start >/dev/null; fi)
+Apr  4 16:32:07 hostname-here NetworkManager[740]: <info>  [1617629527.1101] manager: NetworkManager state is now CONNECTED_GLOBAL
+Apr  4 22:00:45 hostname-here dbus-daemon[1094]: [session uid=1000 pid=1094] Successfully activated service 'io.github.celluloid_player.Celluloid'