diff options
| -rw-r--r-- | .pandoc/bold-code.lua | 9 | ||||
| -rw-r--r-- | Makefile | 2 | ||||
| -rw-r--r-- | bp.1 | 140 | ||||
| -rw-r--r-- | bp.1.md | 251 |
4 files changed, 216 insertions, 186 deletions
diff --git a/.pandoc/bold-code.lua b/.pandoc/bold-code.lua new file mode 100644 index 0000000..02ed189 --- /dev/null +++ b/.pandoc/bold-code.lua @@ -0,0 +1,9 @@ +-- Convert code to bold +function Code(el) + return pandoc.Strong(el.text) +end + +-- Convert code blocks to bold and indented +function CodeBlock(el) + return pandoc.BlockQuote({pandoc.Para(pandoc.Strong(el.text))}) +end @@ -21,7 +21,7 @@ $(NAME): $(OBJFILES) bp.c $(CC) $(ALL_FLAGS) -o $@ $(OBJFILES) bp.c bp.1: bp.1.md - pandoc -s $< -t man -o $@ + pandoc --lua-filter=.pandoc/bold-code.lua -s $< -t man -o $@ tags: $(CFILES) bp.c ctags *.c *.h @@ -7,7 +7,7 @@ bp - Bruce\[aq]s Parsing Expression Grammar tool .SH SYNOPSIS .PP -\f[B]bp\f[R] [\f[I]options\&...\f[R]] \f[I]pattern\f[R] [[--] +\f[B]bp\f[R] [\f[I]options\&...\f[R]] \f[I]pattern\f[R] [[\f[B]--\f[R]] \f[I]files\&...\f[R]] .SH DESCRIPTION .PP @@ -60,8 +60,7 @@ instead of treated as literal files. \f[B]-c\f[R], \f[B]--context\f[R] \f[I]N\f[R] The number of lines of context to print. If \f[I]N\f[R] is 0, print only the exact text of the matches. -If \f[I]N\f[R] is \f[B]\f[CB]\[dq]all\[dq]\f[B]\f[R], print the entire -file. +If \f[I]N\f[R] is \f[B]\[lq]all\[rq]\f[R], print the entire file. Otherwise, if \f[I]N\f[R] is a positive integer, print the whole line on which matches occur, as well as the \f[I]N-1\f[R] lines before and after the match. @@ -97,7 +96,7 @@ with one or two patterns. The default mode for bp patterns is \[lq]string pattern mode\[rq]. In string pattern mode, all characters are interpreted literally except for the backslash (\f[B]\[rs]\f[R]), which may be followed by a bp -pattern (see the \f[B]PATTERNS\f[R] section above). +pattern (see the \f[B]PATTERNS\f[R] section below). Optionally, the bp pattern may be terminated by a semicolon (\f[B];\f[R]). .SH PATTERNS @@ -107,9 +106,12 @@ Expression Grammars and regular expression syntax. The syntax is designed to map closely to verbal descriptions of the patterns, and prefix operators are preferred over suffix operators (as is common in regex syntax). -.PP -Some patterns additionally have \[lq]multi-line\[rq] variants, which -means that they include the newline character. +Patterns are whitespace-agnostic, so they work the same regardless of +whether whitespace is present or not, except for string literals +(\f[B]\[aq]...\[aq]\f[R] and \f[B]\[dq]...\[dq]\f[R]), character +literals (\f[B]\[ga]\f[R]), and escape sequences (\f[B]\[rs]\f[R]). +Whitespace between patterns or parts of a pattern should be used for +clarity, but it will not affect the meaning of the pattern. .TP \f[I]pat1 pat2\f[R] A sequence: \f[I]pat1\f[R] followed by \f[I]pat2\f[R] @@ -155,8 +157,8 @@ either end. Escape sequences are not allowed. .TP \f[B]\[ga]\f[R]\f[I]c\f[R] -The literal character \f[I]c\f[R] (e.g.\ **\[ga]\[at]** matches the -\[lq]\[at]\[rq] character) +The literal character \f[I]c\f[R] (e.g.\ \f[B]\[ga]\[at]\f[R] matches +the \[lq]\[at]\[rq] character) .TP \f[B]\[ga]\f[R]\f[I]c1\f[R]\f[B],\f[R]\f[I]c2\f[R] The literal character \f[I]c1\f[R] or \f[I]c2\f[R] @@ -188,40 +190,43 @@ Not \f[I]pat\f[R] Maybe \f[I]pat\f[R] .TP \f[I]N\f[R] \f[I]pat\f[R] -Exactly \f[I]N\f[R] repetitions of \f[I]pat\f[R] (e.g.\ \f[B]5 -\[ga]x\f[R] matches \f[B]\[lq]xxxxx\[rq]\f[R]) +Exactly \f[I]N\f[R] repetitions of \f[I]pat\f[R] +(e.g.\ \f[B]5 \[dq]x\[dq]\f[R] matches \f[B]\[lq]xxxxx\[rq]\f[R]) .TP \f[I]N\f[R] \f[B]-\f[R] \f[I]M\f[R] \f[I]pat\f[R] Between \f[I]N\f[R] and \f[I]M\f[R] repetitions of \f[I]pat\f[R] -(e.g.\ \f[B]2-3 \[ga]x\f[R] matches \f[B]\[lq]xx\[rq]\f[R] or +(e.g.\ \f[B]2-3 \[dq]x\[dq]\f[R] matches \f[B]\[lq]xx\[rq]\f[R] or \f[B]\[lq]xxx\[rq]\f[R]) .TP \f[I]N\f[R]\f[B]+\f[R] \f[I]pat\f[R] -At least \f[I]N\f[R] or more repetitions of \f[I]pat\f[R] (e.g.\ \f[B]2+ -\[ga]x\f[R] matches \f[B]\[lq]xx\[rq]\f[R], \f[B]\[lq]xxx\[rq]\f[R], -\f[B]\[lq]xxxx\[rq]\f[R], etc.) +At least \f[I]N\f[R] or more repetitions of \f[I]pat\f[R] +(e.g.\ \f[B]2+ \[dq]x\[dq]\f[R] matches \f[B]\[lq]xx\[rq]\f[R], +\f[B]\[lq]xxx\[rq]\f[R], \f[B]\[lq]xxxx\[rq]\f[R], etc.) .TP \f[B]*\f[R] \f[I]pat\f[R] -Some \f[I]pat\f[R]s (zero or more, e.g.\ \f[B]* \[ga]x\f[R] matches +Some \f[I]pat\f[R]s (zero or more, e.g.\ \f[B]* \[dq]x\[dq]\f[R] matches \f[B]\[dq]\[lq]\f[R], \f[B]\[rq]x\[lq]\f[R], \f[B]\[rq]xx\[dq]\f[R], etc.) .TP \f[B]+\f[R] \f[I]pat\f[R] -At least one \f[I]pat\f[R]s (e.g.\ \f[B]+ \[ga]x\f[R] matches +At least one \f[I]pat\f[R]s (e.g.\ \f[B]+ \[dq]x\[dq]\f[R] matches \f[B]\[lq]x\[rq]\f[R], \f[B]\[lq]xx\[rq]\f[R], \f[B]\[lq]xxx\[rq]\f[R], etc.) .TP \f[I]repeating-pat\f[R] \f[B]%\f[R] \f[I]sep\f[R] -\f[I]repeating-pat\f[R] separated by \f[I]sep\f[R] (e.g.\ \f[B]*word % -\[ga],\f[R] matches zero or more comma-separated words) +\f[I]repeating-pat\f[R] (see the examples above) separated by +\f[I]sep\f[R] (e.g.\ \f[B]*word % \[dq],\[dq]\f[R] matches zero or more +comma-separated words) .TP \f[B]..\f[R] \f[I]pat\f[R] Any text (except newlines) up to and including \f[I]pat\f[R] .TP \f[B].. %\f[R] \f[I]skip\f[R] \f[I]pat\f[R] Any text (except newlines) up to and including \f[I]pat\f[R], skipping -over instances of \f[I]skip\f[R] (e.g.\ \f[B]\[ga]\[dq]..\[ga]\[dq] % -(\[ga]\[rs].)\f[R]) +over instances of \f[I]skip\f[R] +(e.g.\ \f[B]\[aq]\[dq]\[aq] ..%(\[aq]\[rs]\[aq] .) \[aq]\[dq]\[aq]\f[R] +opening quote, up to closing quote, skipping over backslash followed by +a single character) .TP \f[B]<\f[R] \f[I]pat\f[R] Matches at the current position if \f[I]pat\f[R] matches immediately @@ -234,13 +239,13 @@ match up to maximum number of characters \f[I]pat\f[R] can match (or the length of the current line upto the current position, whichever is smaller). \f[B]Note:\f[R] For fixed-length lookbehinds, this is quite efficient -(e.g.\ \f[B]<(100\[ga]x)\f[R]), however this could cause performance -problems with variable-length lookbehinds (e.g.\ \f[B]<(\[ga]x -0-100\[ga]y)\f[R]). -Also, it is not advised to use \f[B]\[ha]\f[R], \f[B]\[ha]\[ha]\f[R], -\f[B]\[u2005]*\[u2005]*,\f[BI]o\f[B]\f[BI]r\f[B]\[u2005]*\[u2005]*$\f[R] -inside a lookbehind, as they will match against the edges of the -lookbehind slice. +(e.g.\ \f[B]<(100 \[dq]x\[dq])\f[R]), however this could cause +performance problems with variable-length lookbehinds +(e.g.\ \f[B]<(\[dq]x\[dq] 0-100\[dq]y\[dq])\f[R]). +Also, it is worth noting that \f[B]\[ha]\f[R], \f[B]\[ha]\[ha]\f[R], +\f[B]$\f[R], and \f[B]$$\f[R] all match against the edges of the slice, +which may give false positives if you were expecting them to match only +against the edges file or line. .TP \f[B]>\f[R] \f[I]pat\f[R] Matches \f[I]pat\f[R], but does not consume any input (lookahead). @@ -258,19 +263,24 @@ See the \f[B]GRAMMAR FILES\f[R] section for more info. .TP \f[B]\[at]\f[R] \f[I]name\f[R] \f[B]=\f[R] \f[I]pat\f[R] Let \f[I]name\f[R] equal \f[I]pat\f[R] (named capture). -Named captures can be used as backreferences like so: \f[B]\[at]foo=word -\[ga]( foo \[ga])\f[R] (matches \f[B]\[lq]asdf(asdf)\[rq]\f[R] or -\f[B]\[lq]baz(baz)\[rq]\f[R], but not \f[B]\[lq]foo(baz)\[rq]\f[R]) +Named captures can be used as backreferences like so: +\f[B]\[at]foo=word \[ga]( foo \[ga])\f[R] (matches +\f[B]\[lq]asdf(asdf)\[rq]\f[R] or \f[B]\[lq]baz(baz)\[rq]\f[R], but not +\f[B]\[lq]foo(baz)\[rq]\f[R]) .TP -\f[I]pat\f[R] \f[B]=> \[aq]\f[R]\f[I]replacement\f[R]\f[B]\[aq]\f[R] +\f[I]pat\f[R] \f[B]=>\f[R] \f[B]\[dq]\f[R]\f[I]replacement\f[R]\f[B]\[dq]\f[R] Replace \f[I]pat\f[R] with \f[I]replacement\f[R]. -Note: \f[I]replacement\f[R] should be a string, and it may contain +Note: \f[I]replacement\f[R] should be a string (single or double +quoted), and it may contain escape sequences (e.g.\ \f[B]\[rs]n\f[R]) or references to captured values: \f[B]\[at]0\f[R] (the whole of \f[I]pat\f[R]), \f[B]\[at]1\f[R] (the first capture in \f[I]pat\f[R]), \f[B]\[at]\f[R]\f[I]foo\f[R] (the capture named \f[I]foo\f[R] in \f[I]pat\f[R]), etc. -For example, \f[B]\[at]word _ \[at]rest=(*word % _) => \[dq]\[at]rest -\[at]1\[dq]\f[R] +For example, +\f[B]\[at]word _ \[at]rest=(*word % _) => \[dq]\[at]rest:\[rs]n\[rs]t\[at]1\[dq]\f[R] +matches a word followed by whitespace, followed by a series of words and +replaces it with the series of words, a colon, a newline, a tab, and +then the first word. .TP \f[I]pat1\f[R] \f[B]\[ti]\f[R] \f[I]pat2\f[R] Matches when \f[I]pat1\f[R] matches and \f[I]pat2\f[R] can be found @@ -305,47 +315,51 @@ The \f[B]builtins\f[R] grammar file is loaded by default, and it defines a few useful general-purpose patterns. For example, it defines the \f[B]parens\f[R] rule, which matches pairs of matching parentheses, accounting for nested inner parentheses: -.IP -.nf -\f[C] -bp -p \[aq]\[dq]my_func\[dq] parens\[aq] -\f[R] -.fi +.RS +.PP +\f[B]bp -p \[aq]\[dq]my_func\[dq] parens\[aq]\f[R] +.RE .PP \f[B]bp\f[R] also comes with a few grammar files for common programming languages, which may be loaded on demand. These grammar files are not comprehensive syntax definitions, but only some common patterns. For example, the c++ grammar file contains definitions for -\f[B]//\f[R]-style line comments as well as \f[B]/*\&...*/\f[R]-style +\f[B]//\f[R]-style line comments as well as \f[B]/*...*/\f[R]-style block comments. Thus, you can find all comments with the word \[lq]TODO\[rq] with the following command: -.IP -.nf -\f[C] -bp -g c++ -p \[aq]comment\[ti]{TODO}\[aq] *.cpp -\f[R] -.fi +.RS +.PP +\f[B]bp -g c++ -p \[aq]comment \[ti] {TODO}\[aq] *.cpp\f[R] +.RE .SH EXAMPLES -.TP +.PP +Find files containing the string \[lq]foo\[rq] (a string pattern): +.RS +.PP \f[B]ls | bp foo\f[R] -Find files containing the string \[dq]foo\[dq] (a string pattern) -.TP +.RE +.PP +Find files ending with \[lq].c\[rq] and print the name with the +\[lq].c\[rq] replaced with \[lq].h\[rq]: +.RS +.PP \f[B]ls | bp \[aq].c\[rs]$\[aq] -r \[aq].h\[aq]\f[R] -Find files ending with \[dq].c\[dq] and replace the extension with -\[dq].h\[dq] -.TP +.RE +.PP +Find the word \[lq]foobar\[rq], followed by a pair of matching +parentheses in the file \f[I]my_file.py\f[R]: +.RS +.PP \f[B]bp -p \[aq]{foobar} parens\[aq] my_file.py\f[R] -Find the word \f[B]\[dq]foobar\[dq]\f[R], followed by a pair of matching -parentheses in the file \f[I]my_file.py\f[R] -.TP -\f[B]bp -g html -p \[aq]element \[ti] (\[ha]\[ha]\[dq]<a \[dq])\[aq] foo.html\f[R] +.RE +.PP Using the \f[I]html\f[R] grammar, find all \f[I]element\f[R]s matching -the tag \f[I]a\f[R] in the file \f[I]foo.html\f[R] -.TP -\f[B]bp -g python -p \[aq]comment\[ti]{TODO}\[aq] *.py\f[R] -Find all comments with the word \f[B]\[lq]TODO\[rq]\f[R] in local python -files. +the tag \f[I]a\f[R] in the file \f[I]foo.html\f[R]: +.RS +.PP +\f[B]bp -g html -p \[aq]element \[ti] (\[ha]\[ha]\[dq]<a \[dq])\[aq] foo.html\f[R] +.RE .SH AUTHORS Bruce Hill (\f[I]bruce\[at]bruce-hill.com\f[R]). @@ -8,71 +8,68 @@ bp - Bruce\'s Parsing Expression Grammar tool # SYNOPSIS -**bp** -\[*options...*\] -*pattern* -\[\[\--\] *files...*\] +`bp` \[*options...*\] *pattern* \[\[`--`\] *files...*\] # DESCRIPTION -**bp** is a tool that matches parsing expression grammars using a custom +`bp` is a tool that matches parsing expression grammars using a custom syntax. # OPTIONS -**-v**, **\--verbose** +`-v`, `--verbose` : Print debugging information. -**-e**, **\--explain** +`-e`, `--explain` : Print a visual explanation of the matches. -**-j**, **\--json** -: Print a JSON list of the matches. (Pairs with **\--verbose** for more detail) +`-j`, `--json` +: Print a JSON list of the matches. (Pairs with `--verbose` for more detail) -**-l**, **\--list-files** +`-l`, `--list-files` : Print only the names of files containing matches instead of the matches themselves. -**-i**, **\--ignore-case** +`-i`, `--ignore-case` : Perform pattern matching case-insensitively. -**-I**, **\--inplace** +`-I`, `--inplace` : Perform filtering or replacement in-place (i.e. overwrite files with new content). -**-C**, **\--confirm** +`-C`, `--confirm` : During in-place modification of a file, confirm before each modification. -**-r**, **\--replace** *replacement* +`-r`, `--replace` *replacement* : Replace all occurrences of the main pattern with the given string. -**-s**, **\--skip** *pattern* +`-s`, `--skip` *pattern* : While looking for matches, skip over *pattern* occurrences. This can be -useful for behavior like **bp -s string** (avoiding matches inside string +useful for behavior like `bp -s string` (avoiding matches inside string literals). -**-g**, **\--grammar** *grammar-file* -: Load the grammar from the given file. See the **GRAMMAR FILES** section +`-g`, `--grammar` *grammar-file* +: Load the grammar from the given file. See the `GRAMMAR FILES` section for more info. -**-G**, **\--git** -: Use **git** to get a list of files. Remaining file arguments (if any) are -passed to **git \--ls-files** instead of treated as literal files. +`-G`, `--git` +: Use `git` to get a list of files. Remaining file arguments (if any) are +passed to `git --ls-files` instead of treated as literal files. -**-c**, **\--context** *N* +`-c`, `--context` *N* : The number of lines of context to print. If *N* is 0, print only the -exact text of the matches. If *N* is **`"all"`**, print the entire file. +exact text of the matches. If *N* is **"all"**, print the entire file. Otherwise, if *N* is a positive integer, print the whole line on which matches occur, as well as the *N-1* lines before and after the match. The default value for this argument is **1** (print whole lines where matches occur). -**-f**, **\--format** *auto*\|*fancy*\|*plain* +`-f`, `--format` *auto*\|*fancy*\|*plain* : Set the output format. *fancy* includes colors and line numbers, *plain* includes neither, and *auto* (the default) uses *fancy* formatting only when the output is a TTY. -**\--help** +`--help` : Print the usage and exit. *pattern* @@ -81,7 +78,7 @@ pattern (see the **STRING PATTERNS** section below). *files...* : The input files to search. If no input files are provided and data was piped -in, that data will be used instead. If neither are provided, **bp** will search +in, that data will be used instead. If neither are provided, `bp` will search through all files in the current directory and its subdirectories (recursively). @@ -90,118 +87,119 @@ through all files in the current directory and its subdirectories One of the most common use cases for pattern matching tools is matching plain, literal strings, or strings that are primarily plain strings, with one or two -patterns. **bp** is designed around this fact. The default mode for bp patterns +patterns. `bp` is designed around this fact. The default mode for bp patterns is "string pattern mode". In string pattern mode, all characters are -interpreted literally except for the backslash (**\\**), which may be followed -by a bp pattern (see the **PATTERNS** section above). Optionally, the bp -pattern may be terminated by a semicolon (**;**). +interpreted literally except for the backslash (`\`), which may be followed by +a bp pattern (see the **PATTERNS** section below). Optionally, the bp pattern +may be terminated by a semicolon (`;`). # PATTERNS -**bp** patterns are based off of a combination of Parsing Expression Grammars -and regular expression syntax. The syntax is designed to map closely to verbal +`bp` patterns are based off of a combination of Parsing Expression Grammars and +regular expression syntax. The syntax is designed to map closely to verbal descriptions of the patterns, and prefix operators are preferred over suffix -operators (as is common in regex syntax). - -Some patterns additionally have "multi-line" variants, which means that they -include the newline character. +operators (as is common in regex syntax). Patterns are whitespace-agnostic, so +they work the same regardless of whether whitespace is present or not, except +for string literals (`'...'` and `"..."`), character literals (`` ` ``), and +escape sequences (`\`). Whitespace between patterns or parts of a pattern +should be used for clarity, but it will not affect the meaning of the pattern. *pat1 pat2* : A sequence: *pat1* followed by *pat2* -*pat1* **/** *pat2* +*pat1* `/` *pat2* : A choice: *pat1*, or if it doesn\'t match, then *pat2* -**.** +`.` : Any character (excluding newline) -**\^** +`^` : Start of a line -**\^\^** +`^^` : Start of the text -**\$** +`$` : End of a line (does not include newline character) -**\$\$** +`$$` : End of the text -**\_** +`_` : Zero or more whitespace characters, including spaces and tabs, but not newlines. -**\_\_** +`__` : Zero or more whitespace characters, including spaces, tabs, newlines, and comments. Comments are undefined by default, but may be defined by a separate grammar file. See the **GRAMMAR FILES** section for more info. -**\"foo\"**, **\'foo\'** +`"foo"`, `'foo'` : The literal string **"foo"**. Single and double quotes are treated the same. Escape sequences are not allowed. -**{foo}** +`{foo}` : The literal string **"foo"** with word boundaries on either end. Escape sequences are not allowed. -**\`***c* -: The literal character *c* (e.g. **\`@** matches the "@" character) +`` ` ``*c* +: The literal character *c* (e.g. `` `@ `` matches the "@" character) -**\`***c1***,***c2* -: The literal character *c1* or *c2* (e.g. **\`a,e,i,o,u**) +`` ` ``*c1*`,`*c2* +: The literal character *c1* or *c2* (e.g. `` `a,e,i,o,u ``) -**\`***c1***-***c2* -: The character range *c1* to *c2* (e.g. **\`a-z**). Multiple ranges -can be combined with a comma (e.g. **\`a-z,A-Z**). +`` ` ``*c1*`-`*c2* +: The character range *c1* to *c2* (e.g. `` `a-z ``). Multiple ranges +can be combined with a comma (e.g. `` `a-z,A-Z ``). -**\\***esc* -: An escape sequence (e.g. **\\n**, **\\x1F**, **\\033**, etc.) +`\`*esc* +: An escape sequence (e.g. `\n`, `\x1F`, `\033`, etc.) -**\\***esc1***-***esc2* -: An escape sequence range from *esc1* to *esc2* (e.g. **\\x00-x1F**) +`\`*esc1*`-`*esc2* +: An escape sequence range from *esc1* to *esc2* (e.g. `\x00-x1F`) -**\\N** +`\N` : A special case escape that matches a "nodent": one or more newlines followed by the same indentation that occurs on the current line. -**!** *pat* +`!` *pat* : Not *pat* -**\[** *pat* **\]** +`[` *pat* `]` : Maybe *pat* *N* *pat* -: Exactly *N* repetitions of *pat* (e.g. **5 \`x** matches **"xxxxx"**) +: Exactly *N* repetitions of *pat* (e.g. `5 "x"` matches **"xxxxx"**) -*N* **-** *M* *pat* -: Between *N* and *M* repetitions of *pat* (e.g. **2-3 \`x** -matches **"xx"** or **"xxx"**) +*N* `-` *M* *pat* +: Between *N* and *M* repetitions of *pat* (e.g. `2-3 "x"` matches **"xx"** or +**"xxx"**) -*N***+** *pat* -: At least *N* or more repetitions of *pat* (e.g. **2+ \`x** matches +*N*`+` *pat* +: At least *N* or more repetitions of *pat* (e.g. `2+ "x"` matches **"xx"**, **"xxx"**, **"xxxx"**, etc.) -**\*** *pat* -: Some *pat*s (zero or more, e.g. **\* \`x** matches **""**, **"x"**, -**"xx"**, etc.) +`*` *pat* +: Some *pat*s (zero or more, e.g. `* "x"` matches **""**, **"x"**, **"xx"**, +etc.) -**+** *pat* -: At least one *pat*s (e.g. **\+ \`x** matches **"x"**, **"xx"**, -**"xxx"**, etc.) +`+` *pat* +: At least one *pat*s (e.g. `+ "x"` matches **"x"**, **"xx"**, **"xxx"**, etc.) -*repeating-pat* **%** *sep* -: *repeating-pat* separated by *sep* (e.g. **\*word % \`,** matches -zero or more comma-separated words) +*repeating-pat* `%` *sep* +: *repeating-pat* (see the examples above) separated by *sep* (e.g. `*word % +","` matches zero or more comma-separated words) -**..** *pat* +`..` *pat* : Any text (except newlines) up to and including *pat* -**.. %** *skip* *pat* -: Any text (except newlines) up to and including *pat*, skipping over -instances of *skip* (e.g. **\`\"..\`\" % (\`\\.)**) +`.. %` *skip* *pat* +: Any text (except newlines) up to and including *pat*, skipping over instances +of *skip* (e.g. `'"' ..%('\' .) '"'` opening quote, up to closing quote, +skipping over backslash followed by a single character) -**\<** *pat* +`<` *pat* : Matches at the current position if *pat* matches immediately before the current position (lookbehind). Conceptually, you can think of this as creating a file containing only the *N* characters immediately before the current @@ -209,56 +207,59 @@ position and attempting to match *pat* on that file, for all values of *N* from the minimum number of characters *pat* can match up to maximum number of characters *pat* can match (or the length of the current line upto the current position, whichever is smaller). **Note:** For fixed-length lookbehinds, this -is quite efficient (e.g. **\<(100\`x)**), however this could cause performance -problems with variable-length lookbehinds (e.g. **\<(\`x 0-100\`y)**). Also, -it is not advised to use **\^**, **\^\^**, **$**, or **$$** inside a lookbehind, -as they will match against the edges of the lookbehind slice. +is quite efficient (e.g. `<(100 "x")`), however this could cause performance +problems with variable-length lookbehinds (e.g. `<("x" 0-100"y")`). Also, it is +worth noting that `^`, `^^`, `$`, and `$$` all match against the edges of the +slice, which may give false positives if you were expecting them to match only +against the edges file or line. -**\>** *pat* +`>` *pat* : Matches *pat*, but does not consume any input (lookahead). -**\@** *pat* +`@` *pat* : Capture *pat* -**foo** -: The named pattern whose name is **"foo"**. Pattern names come from definitions in -grammar files or from named captures. Pattern names may contain dashes (**-**), -but not underscores (**\_**), since the underscore is used to match whitespace. -See the **GRAMMAR FILES** section for more info. +`foo` +: The named pattern whose name is **"foo"**. Pattern names come from +definitions in grammar files or from named captures. Pattern names may contain +dashes (`-`), but not underscores (`_`), since the underscore is used to match +whitespace. See the **GRAMMAR FILES** section for more info. -**\@** *name* **=** *pat* +`@` *name* `=` *pat* : Let *name* equal *pat* (named capture). Named captures can be used as -backreferences like so: **\@foo=word \`( foo \`)** (matches **"asdf(asdf)"** or +backreferences like so: `` @foo=word `( foo `) `` (matches **"asdf(asdf)"** or **"baz(baz)"**, but not **"foo(baz)"**) -*pat* **=\> \'***replacement***\'** -: Replace *pat* with *replacement*. Note: *replacement* should be a -string, and it may contain references to captured values: **\@0** (the whole of -*pat*), **\@1** (the first capture in *pat*), **\@***foo* (the capture -named *foo* in *pat*), etc. For example, **\@word \_ \@rest=(\*word % \_) -=\> \"\@rest \@1\"** +*pat* `=>` `"`*replacement*`"` +: Replace *pat* with *replacement*. Note: *replacement* should be a string +(single or double quoted), and it may contain escape sequences (e.g. `\n`) or +references to captured values: `@0` (the whole of *pat*), `@1` (the first +capture in *pat*), `@`*foo* (the capture named *foo* in *pat*), etc. For +example, `@word _ @rest=(*word % _) => "@rest:\n\t@1"` matches a word followed +by whitespace, followed by a series of words and replaces it with the series +of words, a colon, a newline, a tab, and then the first word. -*pat1* **~** *pat2* +*pat1* `~` *pat2* : Matches when *pat1* matches and *pat2* can be found within the text of that -match. (e.g. **comment ~ {TODO}** matches comments that contain the word +match. (e.g. `comment ~ {TODO}` matches comments that contain the word **"TODO"**) -*pat1* **!~** *pat2* +*pat1* `!~` *pat2* : Matches when *pat1* matches, but *pat2* can not be found within the text of -that match. (e.g. **comment ~ {IGNORE}** matches only comments that do not +that match. (e.g. `comment ~ {IGNORE}` matches only comments that do not contain the word **"IGNORE"**) -*name***:** *pat* +*name*`:` *pat* : Define *name* to mean *pat* (pattern definition) -**(!)** *error-pat* +`(!)` *error-pat* : If *error-pat* matches, **bp** will not print any results in this file and instead print an error message to **STDERR** highlighting the matching position of *error-pat* in the file and printing the text of *error-pat* as an error message. Then, **bp** will exit with a failure status and not process any further files. -**\#** *comment* +`#` *comment* : A line comment @@ -277,30 +278,36 @@ bp -p '"my_func" parens' **bp** also comes with a few grammar files for common programming languages, which may be loaded on demand. These grammar files are not comprehensive syntax definitions, but only some common patterns. For example, the c++ grammar file -contains definitions for **//**-style line comments as well as -**/\*...\*/**-style block comments. Thus, you can find all comments with the -word "TODO" with the following command: +contains definitions for `//`-style line comments as well as `/*...*/`-style +block comments. Thus, you can find all comments with the word "TODO" with the +following command: ``` -bp -g c++ -p 'comment~{TODO}' *.cpp +bp -g c++ -p 'comment ~ {TODO}' *.cpp ``` # EXAMPLES -**ls \| bp foo** -: Find files containing the string \"foo\" (a string pattern) +Find files containing the string "foo" (a string pattern): +``` +ls | bp foo +``` -**ls \| bp \'.c\\\$\' -r \'.h\'** -: Find files ending with \".c\" and replace the extension with \".h\" +Find files ending with ".c" and print the name with the ".c" replaced with ".h": +``` +ls | bp '.c\$' -r '.h' +``` -**bp -p \'{foobar} parens\' my_file.py** -: Find the word **\"foobar\"**, followed by a pair of matching parentheses in -the file *my_file.py* +Find the word "foobar", followed by a pair of matching parentheses in the file +*my_file.py*: +``` +bp -p '{foobar} parens' my_file.py +``` -**bp -g html -p \'element ~ (^^\"\<a \")\' foo.html** -: Using the *html* grammar, find all *element*s matching the tag *a* in the -file *foo.html* +Using the *html* grammar, find all *element*s matching the tag *a* in the file +*foo.html*: +``` +bp -g html -p 'element ~ (^^"<a ")' foo.html +``` -**bp -g python -p \'comment~{TODO}\' \*.py** -: Find all comments with the word **"TODO"** in local python files. |