Bash improvements (#1443)

A bunch for improvements for Bash.

components/prism-bash.js

@@ -1,84 +1,197 @@
 (function(Prism) {
+	// $ set | grep '^[A-Z][^[:space:]]*=' | cut -d= -f1 | tr '\n' '|'
+	// + LC_ALL, RANDOM, REPLY, SECONDS.
+	// + make sure PS1..4 are here as they are not always set,
+	// - some useless things.
+	var envVars = '\\b(?:BASH|BASHOPTS|BASH_ALIASES|BASH_ARGC|BASH_ARGV|BASH_CMDS|BASH_COMPLETION_COMPAT_DIR|BASH_LINENO|BASH_REMATCH|BASH_SOURCE|BASH_VERSINFO|BASH_VERSION|COLORTERM|COLUMNS|COMP_WORDBREAKS|DBUS_SESSION_BUS_ADDRESS|DEFAULTS_PATH|DESKTOP_SESSION|DIRSTACK|DISPLAY|EUID|GDMSESSION|GDM_LANG|GNOME_KEYRING_CONTROL|GNOME_KEYRING_PID|GPG_AGENT_INFO|GROUPS|HISTCONTROL|HISTFILE|HISTFILESIZE|HISTSIZE|HOME|HOSTNAME|HOSTTYPE|IFS|INSTANCE|JOB|LANG|LANGUAGE|LC_ADDRESS|LC_ALL|LC_IDENTIFICATION|LC_MEASUREMENT|LC_MONETARY|LC_NAME|LC_NUMERIC|LC_PAPER|LC_TELEPHONE|LC_TIME|LESSCLOSE|LESSOPEN|LINES|LOGNAME|LS_COLORS|MACHTYPE|MAILCHECK|MANDATORY_PATH|NO_AT_BRIDGE|OLDPWD|OPTERR|OPTIND|ORBIT_SOCKETDIR|OSTYPE|PAPERSIZE|PATH|PIPESTATUS|PPID|PS1|PS2|PS3|PS4|PWD|RANDOM|REPLY|SECONDS|SELINUX_INIT|SESSION|SESSIONTYPE|SESSION_MANAGER|SHELL|SHELLOPTS|SHLVL|SSH_AUTH_SOCK|TERM|UID|UPSTART_EVENTS|UPSTART_INSTANCE|UPSTART_JOB|UPSTART_SESSION|USER|WINDOWID|XAUTHORITY|XDG_CONFIG_DIRS|XDG_CURRENT_DESKTOP|XDG_DATA_DIRS|XDG_GREETER_DATA_DIR|XDG_MENU_PREFIX|XDG_RUNTIME_DIR|XDG_SEAT|XDG_SEAT_PATH|XDG_SESSION_DESKTOP|XDG_SESSION_ID|XDG_SESSION_PATH|XDG_SESSION_TYPE|XDG_VTNR|XMODIFIERS)\\b';
 	var insideString = {
-		variable: [
-			// Arithmetic Environment
+		'environment': {
+			pattern: RegExp("\\$" + envVars),
+			alias: 'constant'
+		},
+		'variable': [
+			// [0]: Arithmetic Environment
 			{
 				pattern: /\$?\(\([\s\S]+?\)\)/,
+				greedy: true,
 				inside: {
 					// If there is a $ sign at the beginning highlight $(( and )) as variable
-					variable: [{
+					'variable': [
+						{
 							pattern: /(^\$\(\([\s\S]+)\)\)/,
 							lookbehind: true
 						},
 						/^\$\(\(/
 					],
-					number: /\b0x[\dA-Fa-f]+\b|(?:\b\d+\.?\d*|\B\.\d+)(?:[Ee]-?\d+)?/,
+					'number': /\b0x[\dA-Fa-f]+\b|(?:\b\d+\.?\d*|\B\.\d+)(?:[Ee]-?\d+)?/,
 					// Operators according to https://www.gnu.org/software/bash/manual/bashref.html#Shell-Arithmetic
-					operator: /--?|-=|\+\+?|\+=|!=?|~|\*\*?|\*=|\/=?|%=?|<<=?|>>=?|<=?|>=?|==?|&&?|&=|\^=?|\|\|?|\|=|\?|:/,
+					'operator': /--?|-=|\+\+?|\+=|!=?|~|\*\*?|\*=|\/=?|%=?|<<=?|>>=?|<=?|>=?|==?|&&?|&=|\^=?|\|\|?|\|=|\?|:/,
 					// If there is no $ sign at the beginning highlight (( and )) as punctuation
-					punctuation: /\(\(?|\)\)?|,|;/
+					'punctuation': /\(\(?|\)\)?|,|;/
+				}
+			},
+			// [1]: Command Substitution
+			{
+				pattern: /\$\((?:\([^)]+\)|[^()])+\)|`[^`]+`/,
+				greedy: true,
+				inside: {
+					'variable': /^\$\(|^`|\)$|`$/
 				}
 			},
-			// Command Substitution
+			// [2]: Brace expansion
 			{
-				pattern: /\$\([^)]+\)|`[^`]+`/,
+				pattern: /\$\{[^}]+\}/,
 				greedy: true,
 				inside: {
-					variable: /^\$\(|^`|\)$|`$/
+					'operator': /:[-=?+]?|[!\/]|##?|%%?|\^\^?|,,?/,
+					'punctuation': /[\[\]]/,
+					'environment': {
+						pattern: RegExp("(\\{)" + envVars),
+						lookbehind: true,
+						alias: 'constant'
+					}
 				}
 			},
-			/\$(?:[\w#?*!@]+|\{[^}]+\})/i
-		]
+			/\$(?:\w+|[#?*!@$])/
+		],
+		// Escape sequences from echo and printf's manuals, and escaped quotes.
+		'entity': /\\(?:[abceEfnrtv\\"]|O?[0-7]{1,3}|x[0-9a-fA-F]{1,2}|u[0-9a-fA-F]{4}|U[0-9a-fA-F]{8})/
 	};
 
 	Prism.languages.bash = {
 		'shebang': {
-			pattern: /^#!\s*\/bin\/bash|^#!\s*\/bin\/sh/,
+			pattern: /^#!\s*\/.*/,
 			alias: 'important'
 		},
 		'comment': {
-			pattern: /(^|[^"{\\])#.*/,
+			pattern: /(^|[^"{\\$])#.*/,
+			lookbehind: true
+		},
+		'function-name': [
+			// a) function foo {
+			// b) foo() {
+			// c) function foo() {
+			// but not “foo {”
+			{
+				// a) and c)
+				pattern: /(\bfunction\s+)\w+(?=(?:\s*\(?:\s*\))?\s*\{)/,
+				lookbehind: true,
+				alias: 'function'
+			},
+			{
+				// b)
+				pattern: /\b\w+(?=\s*\(\s*\)\s*\{)/,
+				alias: 'function'
+			}
+		],
+		// Highlight variable names as variables in for and select beginnings.
+		'for-or-select': {
+			pattern: /(\b(?:for|select)\s+)\w+(?=\s+in\s)/,
+			alias: 'variable',
+			lookbehind: true
+		},
+		// Highlight variable names as variables in the left-hand part
+		// of assignments (“=” and “+=”).
+		'assign-left': {
+			pattern: /(^|[\s;|&]|[<>]\()\w+(?=\+?=)/,
+			inside: {
+				'environment': {
+					pattern: RegExp("(^|[\\s;|&]|[<>]\\()" + envVars),
+					lookbehind: true,
+					alias: 'constant'
+				}
+			},
+			alias: 'variable',
 			lookbehind: true
 		},
 		'string': [
-			//Support for Here-Documents https://en.wikipedia.org/wiki/Here_document
+			// Support for Here-documents https://en.wikipedia.org/wiki/Here_document
 			{
-				pattern: /((?:^|[^<])<<\s*)["']?(\w+?)["']?\s*\r?\n(?:[\s\S])*?\r?\n\2/,
+				pattern: /((?:^|[^<])<<-?\s*)(\w+?)\s*(?:\r?\n|\r)(?:[\s\S])*?(?:\r?\n|\r)\2/,
 				lookbehind: true,
 				greedy: true,
 				inside: insideString
 			},
+			// Here-document with quotes around the tag
+			// → No expansion (so no “inside”).
+			{
+				pattern: /((?:^|[^<])<<-?\s*)(["'])(\w+)\2\s*(?:\r?\n|\r)(?:[\s\S])*?(?:\r?\n|\r)\3/,
+				lookbehind: true,
+				greedy: true
+			},
+			// “Normal” string
 			{
 				pattern: /(["'])(?:\\[\s\S]|\$\([^)]+\)|`[^`]+`|(?!\1)[^\\])*\1/,
 				greedy: true,
 				inside: insideString
 			}
 		],
+		'environment': {
+			pattern: RegExp("\\$?" + envVars),
+			alias: 'constant'
+		},
 		'variable': insideString.variable,
-		// Originally based on http://ss64.com/bash/
 		'function': {
-			pattern: /(^|[\s;|&])(?:add|alias|apropos|apt|apt-cache|apt-get|aptitude|aspell|automysqlbackup|awk|basename|bash|bc|bconsole|bg|builtin|bzip2|cal|cat|cd|cfdisk|chgrp|chkconfig|chmod|chown|chroot|cksum|clear|cmp|comm|command|cp|cron|crontab|csplit|curl|cut|date|dc|dd|ddrescue|debootstrap|df|diff|diff3|dig|dir|dircolors|dirname|dirs|dmesg|du|egrep|eject|enable|env|ethtool|eval|exec|expand|expect|export|expr|fdformat|fdisk|fg|fgrep|file|find|fmt|fold|format|free|fsck|ftp|fuser|gawk|getopts|git|gparted|grep|groupadd|groupdel|groupmod|groups|grub-mkconfig|gzip|halt|hash|head|help|hg|history|host|hostname|htop|iconv|id|ifconfig|ifdown|ifup|import|install|ip|jobs|join|kill|killall|less|link|ln|locate|logname|logout|logrotate|look|lpc|lpr|lprint|lprintd|lprintq|lprm|ls|lsof|lynx|make|man|mc|mdadm|mkconfig|mkdir|mke2fs|mkfifo|mkfs|mkisofs|mknod|mkswap|mmv|more|most|mount|mtools|mtr|mutt|mv|nano|nc|netstat|nice|nl|nohup|notify-send|npm|nslookup|op|open|parted|passwd|paste|pathchk|ping|pkill|pnpm|popd|pr|printcap|printenv|printf|ps|pushd|pv|pwd|quota|quotacheck|quotactl|ram|rar|rcp|read|readarray|readonly|reboot|remsync|rename|renice|rev|rm|rmdir|rpm|rsync|scp|screen|sdiff|sed|sendmail|seq|service|sftp|shift|shopt|shutdown|sleep|slocate|sort|source|split|ssh|stat|strace|su|sudo|sum|suspend|swapon|sync|tail|tar|tee|test|time|timeout|times|top|touch|tr|traceroute|trap|tsort|tty|type|ulimit|umask|umount|unalias|uname|unexpand|uniq|units|unrar|unshar|unzip|update-grub|uptime|useradd|userdel|usermod|users|uudecode|uuencode|vdir|vi|vim|virsh|vmstat|wait|watch|wc|wget|whereis|which|who|whoami|write|xargs|xdg-open|yarn|yes|zip|zypper)(?=$|[\s;|&])/,
+			pattern: /(^|[\s;|&]|[<>]\()(?:add|apropos|apt|aptitude|apt-cache|apt-get|aspell|automysqlbackup|awk|basename|bash|bc|bconsole|bg|bzip2|cal|cat|cfdisk|chgrp|chkconfig|chmod|chown|chroot|cksum|clear|cmp|column|comm|cp|cron|crontab|csplit|curl|cut|date|dc|dd|ddrescue|debootstrap|df|diff|diff3|dig|dir|dircolors|dirname|dirs|dmesg|du|egrep|eject|env|ethtool|expand|expect|expr|fdformat|fdisk|fg|fgrep|file|find|fmt|fold|format|free|fsck|ftp|fuser|gawk|git|gparted|grep|groupadd|groupdel|groupmod|groups|grub-mkconfig|gzip|halt|head|hg|history|host|hostname|htop|iconv|id|ifconfig|ifdown|ifup|import|install|ip|jobs|join|kill|killall|less|link|ln|locate|logname|logrotate|look|lpc|lpr|lprint|lprintd|lprintq|lprm|ls|lsof|lynx|make|man|mc|mdadm|mkconfig|mkdir|mke2fs|mkfifo|mkfs|mkisofs|mknod|mkswap|mmv|more|most|mount|mtools|mtr|mutt|mv|nano|nc|netstat|nice|nl|nohup|notify-send|npm|nslookup|op|open|parted|passwd|paste|pathchk|ping|pkill|pnpm|popd|pr|printcap|printenv|ps|pushd|pv|quota|quotacheck|quotactl|ram|rar|rcp|reboot|remsync|rename|renice|rev|rm|rmdir|rpm|rsync|scp|screen|sdiff|sed|sendmail|seq|service|sftp|sh|shellcheck|shuf|shutdown|sleep|slocate|sort|split|ssh|stat|strace|su|sudo|sum|suspend|swapon|sync|tac|tail|tar|tee|time|timeout|top|touch|tr|traceroute|tsort|tty|umount|uname|unexpand|uniq|units|unrar|unshar|unzip|update-grub|uptime|useradd|userdel|usermod|users|uudecode|uuencode|v|vdir|vi|vim|virsh|vmstat|wait|watch|wc|wget|whereis|which|who|whoami|write|xargs|xdg-open|yarn|yes|zenity|zip|zsh|zypper)(?=$|[)\s;|&])/,
 			lookbehind: true
 		},
 		'keyword': {
-			pattern: /(^|[\s;|&])(?:let|:|\.|if|then|else|elif|fi|for|break|continue|while|in|case|function|select|do|done|until|echo|exit|return|set|declare)(?=$|[\s;|&])/,
+			pattern: /(^|[\s;|&]|[<>]\()(?:if|then|else|elif|fi|for|while|in|case|esac|function|select|do|done|until)(?=$|[)\s;|&])/,
 			lookbehind: true
 		},
+		// https://www.gnu.org/software/bash/manual/html_node/Shell-Builtin-Commands.html
+		'builtin': {
+			pattern: /(^|[\s;|&]|[<>]\()(?:\.|:|break|cd|continue|eval|exec|exit|export|getopts|hash|pwd|readonly|return|shift|test|times|trap|umask|unset|alias|bind|builtin|caller|command|declare|echo|enable|help|let|local|logout|mapfile|printf|read|readarray|source|type|typeset|ulimit|unalias|set|shopt)(?=$|[)\s;|&])/,
+			lookbehind: true,
+			// Alias added to make those easier to distinguish from strings.
+			alias: 'class-name'
+		},
 		'boolean': {
-			pattern: /(^|[\s;|&])(?:true|false)(?=$|[\s;|&])/,
+			pattern: /(^|[\s;|&]|[<>]\()(?:true|false)(?=$|[)\s;|&])/,
 			lookbehind: true
 		},
-		'operator': /&&?|\|\|?|==?|!=?|<<<?|>>|<=?|>=?|=~/,
-		'punctuation': /\$?\(\(?|\)\)?|\.\.|[{}[\];]/
+		'file-descriptor': {
+			pattern: /\B&\d\b/,
+			alias: 'important'
+		},
+		'operator': {
+			// Lots of redirections here, but not just that.
+			pattern: /\d?<>|>\||\+=|==?|!=?|=~|<<[<-]?|[&\d]?>>|\d?[<>]&?|&[>&]?|\|[&|]?|<=?|>=?/,
+			inside: {
+				'file-descriptor': {
+					pattern: /^\d/,
+					alias: 'important'
+				}
+			}
+		},
+		'punctuation': /\$?\(\(?|\)\)?|\.\.|[{}[\];\\]/,
+		'number': {
+			pattern: /(^|\s)(?:[1-9]\d*|0)(?:[.,]\d+)?\b/,
+			lookbehind: true
+		}
 	};
 
+	/* Patterns in command substitution. */
+	var toBeCopied = [
+		'comment',
+		'function-name',
+		'for-or-select',
+		'assign-left',
+		'string',
+		'environment',
+		'function',
+		'keyword',
+		'builtin',
+		'boolean',
+		'file-descriptor',
+		'operator',
+		'punctuation',
+		'number'
+	];
 	var inside = insideString.variable[1].inside;
-	inside.string = Prism.languages.bash.string;
-	inside['function'] = Prism.languages.bash['function'];
-	inside.keyword = Prism.languages.bash.keyword;
-	inside['boolean'] = Prism.languages.bash['boolean'];
-	inside.operator = Prism.languages.bash.operator;
-	inside.punctuation = Prism.languages.bash.punctuation;
-
+	for(var i = 0; i < toBeCopied.length; i++) {
+		inside[toBeCopied[i]] = Prism.languages.bash[toBeCopied[i]];
+	}
+
 	Prism.languages.shell = Prism.languages.bash;
 })(Prism);

tests/languages/bash/arithmetic_environment_feature.test

@@ -50,4 +50,4 @@ for (( NUM=1 ; NUM<=1000 ; NUM++ ))
 
 ----------------------------------------------------
 
-Checks arithmetic environments
+Checks arithmetic environments