diff options
| -rw-r--r-- | bonus/w3m.toml | 2 | ||||
| -rw-r--r-- | doc/config.md | 99 | ||||
| -rw-r--r-- | doc/localcgi.md | 2 | ||||
| -rw-r--r-- | res/config.toml | 8 | ||||
| -rw-r--r-- | src/display/lineedit.nim | 18 | ||||
| -rw-r--r-- | src/local/container.nim | 166 | ||||
| -rw-r--r-- | src/utils/strwidth.nim | 30 |
7 files changed, 266 insertions, 59 deletions
diff --git a/bonus/w3m.toml b/bonus/w3m.toml index 63b07ecc..5a92b8c8 100644 --- a/bonus/w3m.toml +++ b/bonus/w3m.toml @@ -24,7 +24,7 @@ C-a = 'pager.cursorLineBegin()' '$' = 'pager.cursorLineEnd()' C-e = 'pager.cursorLineEnd()' w = 'pager.cursorNextWord()' -W = 'pager.cursorPrevWord()' +W = 'pager.cursorWordBegin()' '<' = 'n => pager.pageLeft(n)' '>' = 'n => pager.pageRight(n)' '.' = 'n => pager.scrollLeft(n)' diff --git a/doc/config.md b/doc/config.md index dcc63d6c..cf5cf744 100644 --- a/doc/config.md +++ b/doc/config.md @@ -43,6 +43,10 @@ examples. * [Appendix](#appendix) * [Regex handling](#regex-handling) * [Path handling](#path-handling) + * [Word types](#word-types) + * [w3m word](#w3m-word) + * [vi word](#vi-word) + * [Big word](#big-word) <!-- MANON --> @@ -122,7 +126,7 @@ Following is a list of encoding options: <tr> <td>document-charset</td> -<td>string/array</td> +<td>array of charset label strings</td> <td>List of character sets for loading documents.<br> All listed character sets are enumerated until the document has been decoded without errors. In HTML, meta tags and the BOM may override this with a @@ -315,19 +319,17 @@ Following is a list of display options: <tr> <td>color-mode</td> -<td>"monochrome"/"ansi"/"eight-bit","8bit"/"true-color","24bit"/"auto"</td> +<td>"monochrome" / "ansi" / "eight-bit" / "true-color" / "auto"</td> <td>Set the color mode. "auto" for automatic detection, "monochrome" for black on white, "ansi" for ansi colors, "eight-bit" for 256-color mode, and "true-color" for true colors.<br> -"8bit" is a legacy alias of "eight-bit". "24bit" is a legacy alias of -"true-color". (The only difference is that when overriding these values with -the `-o` command line switch, you can use "eight-bit" and "true-color" -without quoting.)</td> +"8bit" is accepted as a legacy alias of "eight-bit". "24bit" is accepted as +a legacy alias of "true-color".</td> </tr> <tr> <td>format-mode</td> -<td>"auto"/["bold", "italic", "underline", "reverse", "strike", "overline", +<td>"auto" / ["bold", "italic", "underline", "reverse", "strike", "overline", "blink"]</td> <td>Specifies output formatting modes. Accepts the string "auto" or an array of specific attributes. An empty array (`[]`) disables formatting @@ -349,7 +351,7 @@ overlines are substituted by underlines on the previous line.</td> <tr> <td>alt-screen</td> -<td>"auto"/boolean</td> +<td>"auto" / boolean</td> <td>Enable/disable the alternative screen.</td> </tr> @@ -529,7 +531,7 @@ false for all websites.</td> <tr> <td>third-party-cookie</td> -<td>regex/array of regexes</td> +<td>array of regexes</td> <td>Domains for which third-party cookies are allowed on this domain. Note: this only works for buffers which share the same cookie jar.<br> Note: regexes are handled according to the [regex handling](#regex-handling) @@ -705,13 +707,29 @@ Note: this does not suspend buffer processes.</td> </tr> <tr> -<td>`pager.cursorNextWord()`</td> -<td>Move the cursor to the beginning of the next word.</td> +<td>`pager.cursorNextWord()`, `pager.cursorNextViWord()`, +`pager.cursorNextBigWord()`</td> +<td>Move the cursor to the beginning of the next [word](#word-types).</td> </tr> <tr> -<td>`pager.cursorPrevWord()`</td> -<td>Move the cursor to the end of the previous word.</td> +<td>`pager.cursorPrevWord()`, `pager.cursorPrevViWord()`, +`pager.cursorPrevBigWord()`</td> +<td>Move the cursor to the end of the previous [word](#word-types).</td> +</tr> + +<tr> +<td>`pager.cursorWordEnd()`, `pager.cursorViWordEnd()`, +`pager.cursorBigWordEnd()`</td> +<td>Move the cursor to the end of the current [word](#word-types), or if already +there, to the end of the next word.</td> +</tr> + +<tr> +<td>`pager.cursorWordBegin()`, `pager.cursorViWordBegin()`, +`pager.cursorBigWordBegin()`</td> +<td>Move the cursor to the beginning of the current [word](#word-types), or if +already there, to the end of the previous word.</td> </tr> <tr> @@ -853,7 +871,7 @@ buffer.</td> <tr> <td>`pager.toggleSource()`</td> -<td>If viewing a HTML buffer, open a new buffer with its source. Otherwise, +<td>If viewing an HTML buffer, open a new buffer with its source. Otherwise, open the current buffer's contents as HTML.</td> </tr> @@ -1131,12 +1149,12 @@ value is `false`.</td> </tr> <tr> -<td>`line.clearWord(bounds)`</td> +<td>`line.clearWord()`</td> <td>Delete word before cursor</td> </tr> <tr> -<td>`line.killWord(bounds)`</td> +<td>`line.killWord()`</td> <td>Delete word after cursor</td> </tr> @@ -1151,12 +1169,12 @@ value is `false`.</td> </tr> <tr> -<td>`line.prevWord(bounds)`</td> +<td>`line.prevWord()`</td> <td>Move cursor to the previous word by one character</td> </tr> <tr> -<td>`line.nextWord(bounds)`</td> +<td>`line.nextWord()`</td> <td>Move cursor to the previous word by one character</td> </tr> @@ -1187,10 +1205,11 @@ value is `false`.</td> </table> -Some of these entries have an optional `bounds` parameter. If passed, this -must be a JavaScript function that expects one parameter (the current -unicode character), and returns true if the passed character should count -as a word boundary. +Note: to facilitate URL editing, the line editor has a different definition +of what a word is than the pager. For the line editor, a word is either a +sequence of alphanumeric characters, or any single non-alphanumeric +character. (This means that e.g. `https://` consists of four words: `https`, +`:`, `/` and `/`.) ```Examples: # Control+A moves the cursor to the beginning of the line. @@ -1199,9 +1218,6 @@ as a word boundary. # Escape+D deletes everything after the cursor until it reaches a word-breaking # character. 'M-d' = 'line.killWord()' - -# Control+W deletes everything before the cursor until it reaches a space. -'C-w' = 'line.clearWord(x => x == " ")' ``` ## Appendix @@ -1237,6 +1253,39 @@ using the syntax `${%VARIABLE}`: * `${%CHA_LIBEXEC_DIR}`: the directory for all executables Chawan uses for operation. By default, this is `${%CHA_BIN_DIR}/../libexec/chawan`. +### Word types + +Word-based pager commands can operate with different definitions of +words. Currently, these are: + +* w3m words +* vi words +* Big words + +#### w3m word + +A w3m word is a sequence of alphanumeric characters. Symbols are treated +in the same way as whitespace. + +#### vi word + +A vi word is a sequence of alphanumeric characters, OR a sequence of symbols. + +vi words may be separated by whitespace; however, symbolic and alphanumeric +vi words do not have to be whitespace-separated. e.g. following character +sequence contains two words: + +``` +hello[]+{}@`! +``` + +#### Big word + +A big word is a sequence of non-whitespace characters. + +It is essentially the same as a w3m word, but with symbols being defined as +non-whitespace. + <!-- MANON ## See also diff --git a/doc/localcgi.md b/doc/localcgi.md index 206a3ef7..1a0d9021 100644 --- a/doc/localcgi.md +++ b/doc/localcgi.md @@ -145,7 +145,7 @@ original URL. Then: * `MAPPED_URI_PASSWORD=` the password part, in this case `password`. If no password was specified, the variable is set to the empty string. * `MAPPED_URI_HOST=` the host part, in this case `host.org` If no host was - specified, the variable is set to the empty string. (An example of an URL + specified, the variable is set to the empty string. (An example of a URL with no host: `about:blank`, here `blank` is the path name.) * `MAPPED_URI_PORT=` the port, in this case `1234`. If no port was specified, the variable is set to the empty string. (In this case, the CGI script is diff --git a/res/config.toml b/res/config.toml index 85ac9aa8..13691234 100644 --- a/res/config.toml +++ b/res/config.toml @@ -84,8 +84,12 @@ l = 'n => pager.cursorRight(n)' '0' = 'pager.cursorLineBegin()' '^' = 'pager.cursorLineTextStart()' '$' = 'pager.cursorLineEnd()' -b = 'pager.cursorPrevWord()' -w = 'pager.cursorNextWord()' +b = 'pager.cursorViWordBegin()' +e = 'pager.cursorViWordEnd()' +w = 'pager.cursorNextViWord()' +B = 'pager.cursorBigWordBegin()' +E = 'pager.cursorBigWordEnd()' +W = 'pager.cursorNextBigWord()' '[' = 'n => pager.cursorPrevLink(n)' ']' = 'n => pager.cursorNextLink(n)' '{' = 'n => pager.cursorPrevParagraph(n)' diff --git a/src/display/lineedit.nim b/src/display/lineedit.nim index 7eef9bfb..7a5067eb 100644 --- a/src/display/lineedit.nim +++ b/src/display/lineedit.nim @@ -208,50 +208,50 @@ proc forward(edit: LineEdit) {.jsfunc.} = if edit.cursorx >= edit.shiftx + edit.maxwidth: edit.invalid = true -proc prevWord(edit: LineEdit, check = opt(BoundaryFunction)) {.jsfunc.} = +proc prevWord(edit: LineEdit) {.jsfunc.} = if edit.cursori == 0: return let (r, len) = edit.news.lastRune(edit.cursori - 1) - if r.breaksWord(check): + if r.breaksWord(): edit.cursori -= len edit.cursorx -= r.width() while edit.cursori > 0: let (r, len) = edit.news.lastRune(edit.cursori - 1) - if r.breaksWord(check): + if r.breaksWord(): break edit.cursori -= len edit.cursorx -= r.width() if edit.cursorx < edit.shiftx: edit.invalid = true -proc nextWord(edit: LineEdit, check = opt(BoundaryFunction)) {.jsfunc.} = +proc nextWord(edit: LineEdit) {.jsfunc.} = if edit.cursori >= edit.news.len: return let oc = edit.cursori var r: Rune fastRuneAt(edit.news, edit.cursori, r) - if r.breaksWord(check): + if r.breaksWord(): edit.cursorx += r.width() else: edit.cursori = oc while edit.cursori < edit.news.len: let pc = edit.cursori fastRuneAt(edit.news, edit.cursori, r) - if r.breaksWord(check): + if r.breaksWord(): edit.cursori = pc break edit.cursorx += r.width() if edit.cursorx >= edit.shiftx + edit.maxwidth: edit.invalid = true -proc clearWord(edit: LineEdit, check = opt(BoundaryFunction)) {.jsfunc.} = +proc clearWord(edit: LineEdit) {.jsfunc.} = let oc = edit.cursori - edit.prevWord(check) + edit.prevWord() if oc != edit.cursori: edit.news.delete(edit.cursori .. oc - 1) edit.invalid = true -proc killWord(edit: LineEdit, check = opt(BoundaryFunction)) {.jsfunc.} = +proc killWord(edit: LineEdit) {.jsfunc.} = if edit.cursori >= edit.news.len: return let oc = edit.cursori diff --git a/src/local/container.nim b/src/local/container.nim index 83ba16f0..fe6e30e5 100644 --- a/src/local/container.nim +++ b/src/local/container.nim @@ -655,28 +655,140 @@ proc cursorLineBegin(container: Container) {.jsfunc.} = proc cursorLineEnd(container: Container) {.jsfunc.} = container.setCursorX(container.currentLineWidth() - 1) -proc cursorNextWord(container: Container) {.jsfunc.} = +type BreakFunc = proc(r: Rune): BreakCategory {.nimcall.} + +proc cursorNextWord(container: Container, breakFunc: BreakFunc) = if container.numLines == 0: return var r: Rune var b = container.currentCursorBytes() var x = container.cursorx + # meow + let currentCat = if b < container.currentLine.len: + container.currentLine.runeAt(b).breakFunc() + else: + BREAK_SPACE + if currentCat != BREAK_SPACE: + # not in space, skip chars that have the same category + while b < container.currentLine.len: + let pb = b + fastRuneAt(container.currentLine, b, r) + if r.breakFunc() != currentCat: + b = pb + break + x += r.twidth(x) + + # skip space while b < container.currentLine.len: let pb = b fastRuneAt(container.currentLine, b, r) - if r.breaksWord(): + if r.breakFunc() != BREAK_SPACE: b = pb break x += r.twidth(x) + if b < container.currentLine.len: + container.setCursorX(x) + else: + if container.cursory < container.numLines - 1: + container.cursorDown() + container.cursorLineBegin() + else: + container.cursorLineEnd() + +proc cursorNextWord(container: Container) {.jsfunc.} = + container.cursorNextWord(breaksWordCat) + +proc cursorNextViWord(container: Container) {.jsfunc.} = + container.cursorNextWord(breaksViWordCat) + +proc cursorNextBigWord(container: Container) {.jsfunc.} = + container.cursorNextWord(breaksBigWordCat) + +proc cursorPrevWord(container: Container, breakFunc: BreakFunc) = + if container.numLines == 0: return + var b = container.currentCursorBytes() + var x = container.cursorx + if container.currentLine.len > 0: + b = min(b, container.currentLine.len - 1) + let currentCat = if b >= 0: + container.currentLine.runeAt(b).breakFunc() + else: + BREAK_SPACE + if currentCat != BREAK_SPACE: + # not in space, skip chars that have the same category + while b >= 0: + let (r, o) = lastRune(container.currentLine, b) + if r.breakFunc() != currentCat: + break + b -= o + x -= r.twidth(x) + + # skip space + while b >= 0: + let (r, o) = lastRune(container.currentLine, b) + if r.breakFunc() != BREAK_SPACE: + break + b -= o + x -= r.twidth(x) + else: + b = -1 + + if b >= 0: + container.setCursorX(x) + else: + if container.cursory > 0: + container.cursorUp() + container.cursorLineEnd() + else: + container.cursorLineBegin() + +proc cursorPrevWord(container: Container) {.jsfunc.} = + container.cursorPrevWord(breaksWordCat) + +proc cursorPrevViWord(container: Container) {.jsfunc.} = + container.cursorPrevWord(breaksViWordCat) + +proc cursorPrevBigWord(container: Container) {.jsfunc.} = + container.cursorPrevWord(breaksBigWordCat) + +proc cursorWordEnd(container: Container, breakFunc: BreakFunc) = + if container.numLines == 0: return + var r: Rune + var b = container.currentCursorBytes() + var x = container.cursorx + var px = x + # if not in space, move to the right by one + if b < container.currentLine.len: + let pb = b + fastRuneAt(container.currentLine, b, r) + if r.breakFunc() == BREAK_SPACE: + b = pb + else: + px = x + x += r.twidth(x) + + # skip space while b < container.currentLine.len: let pb = b fastRuneAt(container.currentLine, b, r) - if not r.breaksWord(): + if r.breakFunc() != BREAK_SPACE: b = pb break x += r.twidth(x) if b < container.currentLine.len: + let currentCat = container.currentLine.runeAt(b).breakFunc() + while b < container.currentLine.len: + let pb = b + fastRuneAt(container.currentLine, b, r) + if r.breakFunc() != currentCat: + b = pb + break + px = x + x += r.twidth(x) + x = px + + if b < container.currentLine.len: container.setCursorX(x) else: if container.cursory < container.numLines - 1: @@ -685,25 +797,50 @@ proc cursorNextWord(container: Container) {.jsfunc.} = else: container.cursorLineEnd() -proc cursorPrevWord(container: Container) {.jsfunc.} = +proc cursorWordEnd(container: Container) {.jsfunc.} = + container.cursorWordEnd(breaksWordCat) + +proc cursorViWordEnd(container: Container) {.jsfunc.} = + container.cursorWordEnd(breaksViWordCat) + +proc cursorBigWordEnd(container: Container) {.jsfunc.} = + container.cursorWordEnd(breaksBigWordCat) + +proc cursorWordBegin(container: Container, breakFunc: BreakFunc) = if container.numLines == 0: return var b = container.currentCursorBytes() var x = container.cursorx + var px = x if container.currentLine.len > 0: b = min(b, container.currentLine.len - 1) - while b >= 0: + if b >= 0: let (r, o) = lastRune(container.currentLine, b) - if r.breaksWord(): - break - b -= o - x -= r.twidth(x) + # if not in space, move to the left by one + if r.breakFunc() != BREAK_SPACE: + b -= o + px = x + x -= r.twidth(x) + # skip space while b >= 0: let (r, o) = lastRune(container.currentLine, b) - if not r.breaksWord(): + if r.breakFunc() != BREAK_SPACE: break b -= o x -= r.twidth(x) + + # move to the last char in the current category + if b >= 0: + let (r, _) = lastRune(container.currentLine, b) + let currentCat = r.breakFunc() + while b >= 0: + let (r, o) = lastRune(container.currentLine, b) + if r.breakFunc() != currentCat: + break + b -= o + px = x + x -= r.twidth(x) + x = px else: b = -1 @@ -716,6 +853,15 @@ proc cursorPrevWord(container: Container) {.jsfunc.} = else: container.cursorLineBegin() +proc cursorWordBegin(container: Container) {.jsfunc.} = + container.cursorWordBegin(breaksWordCat) + +proc cursorViWordBegin(container: Container) {.jsfunc.} = + container.cursorWordBegin(breaksViWordCat) + +proc cursorBigWordBegin(container: Container) {.jsfunc.} = + container.cursorWordBegin(breaksBigWordCat) + proc pageDown(container: Container, n = 1) {.jsfunc.} = container.setFromY(container.fromy + container.height * n) container.setCursorY(container.cursory + container.height * n) diff --git a/src/utils/strwidth.nim b/src/utils/strwidth.nim index 32e8ca7f..5ce2ba52 100644 --- a/src/utils/strwidth.nim +++ b/src/utils/strwidth.nim @@ -2,8 +2,6 @@ import std/strutils import std/unicode import utils/proptable -import js/error -import types/opt import utils/charcategory import utils/map @@ -101,15 +99,25 @@ func padToWidth*(str: string, size: int, schar = '$'): string = func isDigitAscii(r: Rune): bool = return uint32(r) < 128 and char(r) in AsciiDigit +type BreakCategory* = enum + BREAK_ALPHA, BREAK_SPACE, BREAK_SYMBOL + func breaksWord*(r: Rune): bool = return not (r.isDigitAscii() or r.width() == 0 or r.isAlpha()) -type BoundaryFunction* = proc(x: Rune): JSResult[bool] - -proc breaksWord*(r: Rune, check: Opt[BoundaryFunction]): bool = - if check.isSome: - let f = check.get() - let v = f(r) - if v.isSome: #TODO report error? - return v.get() - return r.breaksWord() +func breaksViWordCat*(r: Rune): BreakCategory = + if r.isWhiteSpace(): + return BREAK_SPACE + elif r.breaksWord(): + return BREAK_SYMBOL + return BREAK_ALPHA + +func breaksWordCat*(r: Rune): BreakCategory = + if not r.breaksWord(): + return BREAK_ALPHA + return BREAK_SPACE + +func breaksBigWordCat*(r: Rune): BreakCategory = + if not r.isWhiteSpace(): + return BREAK_ALPHA + return BREAK_SPACE |