summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--stdlib/printf.ml14
-rw-r--r--stdlib/printf.mli38
-rw-r--r--stdlib/scanf.ml100
-rw-r--r--stdlib/scanf.mli290
-rw-r--r--typing/typecore.ml90
5 files changed, 287 insertions, 245 deletions
diff --git a/stdlib/printf.ml b/stdlib/printf.ml
index 5508768dc..c55c64d36 100644
--- a/stdlib/printf.ml
+++ b/stdlib/printf.ml
@@ -217,7 +217,7 @@ let iter_on_format_args fmt add_conv add_char =
and scan_conv skip i =
if i > lim then incomplete_format fmt else
match Sformat.unsafe_get fmt i with
- | '%' | '!' | ',' -> succ i
+ | '%' | '@' | '!' | ',' -> succ i
| 's' | 'S' | '[' -> add_conv skip i 's'
| 'c' | 'C' -> add_conv skip i 'c'
| 'd' | 'i' |'o' | 'u' | 'x' | 'X' | 'N' -> add_conv skip i 'i'
@@ -505,8 +505,10 @@ let scan_format fmt args n pos cont_s cont_a cont_t cont_f cont_m =
and scan_conv spec n widths i =
match Sformat.unsafe_get fmt i with
- | '%' ->
- cont_s n "%" (succ i)
+ | '%' | '@' as c ->
+ cont_s n (String.make 1 c) (succ i)
+ | '!' -> cont_f n (succ i)
+ | ',' -> cont_s n "" (succ i)
| 's' | 'S' as conv ->
let (x : string) = get_arg spec n in
let x = if conv = 's' then x else "\"" ^ String.escaped x ^ "\"" in
@@ -515,6 +517,8 @@ let scan_format fmt args n pos cont_s cont_a cont_t cont_f cont_m =
if i = succ pos then x else
format_string (extract_format fmt pos i widths) x in
cont_s (next_index spec n) s (succ i)
+ | '[' as conv ->
+ bad_conversion_format fmt i conv
| 'c' | 'C' as conv ->
let (x : char) = get_arg spec n in
let s =
@@ -546,6 +550,8 @@ let scan_format fmt args n pos cont_s cont_a cont_t cont_f cont_m =
let n = Sformat.succ_index (get_index spec n) in
let arg = get_arg Spec_none n in
cont_a (next_index spec n) printer arg (succ i)
+ | 'r' as conv ->
+ bad_conversion_format fmt i conv
| 't' ->
let printer = get_arg spec n in
cont_t (next_index spec n) printer (succ i)
@@ -570,8 +576,6 @@ let scan_format fmt args n pos cont_s cont_a cont_t cont_f cont_m =
let s = format_int (extract_format_int 'n' fmt pos i widths) x in
cont_s (next_index spec n) s (succ i)
end
- | ',' -> cont_s n "" (succ i)
- | '!' -> cont_f n (succ i)
| '{' | '(' as conv (* ')' '}' *) ->
let (xf : ('a, 'b, 'c, 'd, 'e, 'f) format6) = get_arg spec n in
let i = succ i in
diff --git a/stdlib/printf.mli b/stdlib/printf.mli
index 83366a532..942ec49b0 100644
--- a/stdlib/printf.mli
+++ b/stdlib/printf.mli
@@ -20,7 +20,7 @@ val fprintf : out_channel -> ('a, out_channel, unit) format -> 'a
[arg1] to [argN] according to the format string [format], and
outputs the resulting string on the channel [outchan].
- The format is a character string which contains two types of
+ The format string is a character string which contains two types of
objects: plain characters, which are simply copied to the output
channel, and conversion specifications, each of which causes
conversion and printing of arguments.
@@ -31,20 +31,23 @@ val fprintf : out_channel -> ('a, out_channel, unit) format -> 'a
In short, a conversion specification consists in the [%] character,
followed by optional modifiers and a type which is made of one or
- two characters. The types and their meanings are:
+ two characters.
- - [d], [i], [n], [l], [L], or [N]: convert an integer argument to
- signed decimal.
- - [u]: convert an integer argument to unsigned decimal.
+ The types and their meanings are:
+
+ - [d], [i]: convert an integer argument to signed decimal.
+ - [u], [n], [l], [L], or [N]: convert an integer argument to
+ unsigned decimal. Warning: [n], [l], [L], and [N] are
+ used for [scanf], and should not be used for [printf].
- [x]: convert an integer argument to unsigned hexadecimal,
using lowercase letters.
- [X]: convert an integer argument to unsigned hexadecimal,
using uppercase letters.
- [o]: convert an integer argument to unsigned octal.
- [s]: insert a string argument.
- - [S]: insert a string argument in OCaml syntax (double quotes, escapes).
+ - [S]: convert a string argument to OCaml syntax (double quotes, escapes).
- [c]: insert a character argument.
- - [C]: insert a character argument in OCaml syntax (single quotes, escapes).
+ - [C]: convert a character argument to OCaml syntax (single quotes, escapes).
- [f]: convert a floating-point argument to decimal notation,
in the style [dddd.ddd].
- [F]: convert a floating-point argument to OCaml syntax ([dddd.]
@@ -54,37 +57,40 @@ val fprintf : out_channel -> ('a, out_channel, unit) format -> 'a
- [g] or [G]: convert a floating-point argument to decimal notation,
in style [f] or [e], [E] (whichever is more compact).
- [B]: convert a boolean argument to the string [true] or [false]
- - [b]: convert a boolean argument (for backward compatibility; do not
- use in new programs).
+ - [b]: convert a boolean argument (deprecated; do not use in new
+ programs).
- [ld], [li], [lu], [lx], [lX], [lo]: convert an [int32] argument to
the format specified by the second letter (decimal, hexadecimal, etc).
- [nd], [ni], [nu], [nx], [nX], [no]: convert a [nativeint] argument to
the format specified by the second letter.
- [Ld], [Li], [Lu], [Lx], [LX], [Lo]: convert an [int64] argument to
the format specified by the second letter.
- - [a]: user-defined printer. Takes two arguments and applies the
+ - [a]: user-defined printer. Take two arguments and apply the
first one to [outchan] (the current output channel) and to the
second argument. The first argument must therefore have type
[out_channel -> 'b -> unit] and the second ['b].
The output produced by the function is inserted in the output of
[fprintf] at the current point.
- - [t]: same as [%a], but takes only one argument (with type
+ - [t]: same as [%a], but take only one argument (with type
[out_channel -> unit]) and apply it to [outchan].
- [\{ fmt %\}]: convert a format string argument. The argument must
have the same type as the internal format string [fmt].
- - [( fmt %)]: format string substitution. Takes a format string
- argument and substitutes it to the internal format string [fmt]
+ - [( fmt %)]: format string substitution. Take a format string
+ argument and substitute it to the internal format string [fmt]
to print following arguments. The argument must have the same
type as the internal format string [fmt].
- [!]: take no argument and flush the output.
- [%]: take no argument and output one [%] character.
- - [,]: the no-op delimiter for conversion specifications.
+ - [\@]: take no argument and output one [\@] character.
+ - [,]: take no argument and do nothing.
The optional [flags] are:
- [-]: left-justify the output (default is right justification).
- [0]: for numerical conversions, pad with zeroes instead of spaces.
- - [+]: for numerical conversions, prefix number with a [+] sign if positive.
- - space: for numerical conversions, prefix number with a space if positive.
+ - [+]: for signed numerical conversions, prefix number with a [+]
+ sign if positive.
+ - space: for signed numerical conversions, prefix number with a
+ space if positive.
- [#]: request an alternate formatting style for numbers.
The optional [width] is an integer indicating the minimal
diff --git a/stdlib/scanf.ml b/stdlib/scanf.ml
index 2bfd45cc6..9c6ecef62 100644
--- a/stdlib/scanf.ml
+++ b/stdlib/scanf.ml
@@ -438,7 +438,7 @@ let int_of_width_opt = function
;;
let int_of_prec_opt = function
- | None -> 0
+ | None -> max_int
| Some prec -> prec
;;
@@ -999,31 +999,51 @@ type char_set =
| Neg_set of string (* Negative (complementary) set. *)
;;
+
(* Char sets are read as sub-strings in the format string. *)
-let read_char_set fmt i =
- let lim = Sformat.length fmt - 1 in
+let scan_range fmt j =
+
+ let len = Sformat.length fmt in
+
+ let buffer = Buffer.create len in
- let rec find_in_set j =
- if j > lim then incomplete_format fmt else
+ let rec scan_closing j =
+ if j >= len then incomplete_format fmt else
match Sformat.get fmt j with
- | ']' -> j
- | _ -> find_in_set (succ j)
-
- and find_set i =
- if i > lim then incomplete_format fmt else
- match Sformat.get fmt i with
- | ']' -> find_in_set (succ i)
- | _ -> find_in_set i in
-
- if i > lim then incomplete_format fmt else
- match Sformat.get fmt i with
- | '^' ->
- let i = succ i in
- let j = find_set i in
- j, Neg_set (Sformat.sub fmt (Sformat.index_of_int i) (j - i))
- | _ ->
- let j = find_set i in
- j, Pos_set (Sformat.sub fmt (Sformat.index_of_int i) (j - i))
+ | ']' -> j, Buffer.contents buffer
+ | '%' ->
+ let j = j + 1 in
+ if j >= len then incomplete_format fmt else
+ begin match Sformat.get fmt j with
+ | '%' | '@' as c ->
+ Buffer.add_char buffer c;
+ scan_closing (j + 1)
+ | c -> bad_conversion fmt j c
+ end
+ | c ->
+ Buffer.add_char buffer c;
+ scan_closing (j + 1) in
+
+ let scan_first_pos j =
+ if j >= len then incomplete_format fmt else
+ match Sformat.get fmt j with
+ | ']' as c ->
+ Buffer.add_char buffer c;
+ scan_closing (j + 1)
+ | _ -> scan_closing j in
+
+ let rec scan_first_neg j =
+ if j >= len then incomplete_format fmt else
+ match Sformat.get fmt j with
+ | '^' ->
+ let j = j + 1 in
+ let k, char_set = scan_first_pos j in
+ k, Neg_set char_set
+ | _ ->
+ let k, char_set = scan_first_pos j in
+ k, Pos_set char_set in
+
+ scan_first_neg j
;;
(* Char sets are now represented as bit vectors that are represented as
@@ -1370,18 +1390,19 @@ let scan_format ib ef fmt rv f =
let width = int_of_width_opt width_opt in
let prec = int_of_prec_opt prec_opt in
match Sformat.get fmt i with
- | '%' as conv ->
- check_char ib conv; scan_fmt ir f (succ i)
+ | '%' | '@' as c ->
+ check_char ib c;
+ scan_fmt ir f (succ i)
| 's' ->
- let i, stp = scan_fmt_stoppers (succ i) in
+ let i, stp = scan_indication (succ i) in
let _x = scan_string stp width ib in
scan_fmt ir (stack f (token_string ib)) (succ i)
| 'S' ->
let _x = scan_String width ib in
scan_fmt ir (stack f (token_string ib)) (succ i)
| '[' (* ']' *) ->
- let i, char_set = read_char_set fmt (succ i) in
- let i, stp = scan_fmt_stoppers (succ i) in
+ let i, char_set = scan_range fmt (succ i) in
+ let i, stp = scan_indication (succ i) in
let _x = scan_chars_in_char_set stp char_set width ib in
scan_fmt ir (stack f (token_string ib)) (succ i)
| ('c' | 'C') when width = 0 ->
@@ -1458,12 +1479,23 @@ let scan_format ib ef fmt rv f =
| c -> bad_conversion fmt i c
- and scan_fmt_stoppers i =
- if i > lim then i - 1, [] else
- match Sformat.get fmt i with
- | '@' when i < lim -> let i = succ i in i, [Sformat.get fmt i]
- | '@' when i = lim -> incomplete_format fmt
- | _ -> i - 1, [] in
+ and scan_indication j =
+ if j > lim then j - 1, [] else
+ match Sformat.get fmt j with
+ | '@' ->
+ let k = j + 1 in
+ if k > lim then j - 1, [] else
+ begin match Sformat.get fmt k with
+ | '%' ->
+ let k = k + 1 in
+ if k > lim then j - 1, [] else
+ begin match Sformat.get fmt k with
+ | '%' | '@' as c -> k, [ c ]
+ | _c -> j - 1, []
+ end
+ | c -> k, [ c ]
+ end
+ | _c -> j - 1, [] in
scan_fmt in
diff --git a/stdlib/scanf.mli b/stdlib/scanf.mli
index 7ab0a23d1..53317d66d 100644
--- a/stdlib/scanf.mli
+++ b/stdlib/scanf.mli
@@ -232,21 +232,14 @@ val bscanf : Scanning.in_channel -> ('a, 'b, 'c, 'd) scanner;;
(** {6 Format string description} *)
-(** The format string is a character string which contains three types of
+(** The format is a character string which contains three types of
objects:
- plain characters, which are simply matched with the characters of the
input (with a special case for space and line feed, see {!Scanf.space}),
- conversion specifications, each of which causes reading and conversion of
one argument for the function [f] (see {!Scanf.conversion}),
- scanning indications to specify boundaries of tokens
- (see scanning {!Scanf.indication}).
-
- As a special convention for format strings, the [\@] character introduces
- an escape for both characters [\@] and [%]: in a format string,
- [\@\@] and [\@%] are respectively equivalent to the plain characters [\@]
- and [%].
- @since 3.13
-*)
+ (see scanning {!Scanf.indication}). *)
(** {7:space The space character in format strings} *)
@@ -269,157 +262,148 @@ val bscanf : Scanning.in_channel -> ('a, 'b, 'c, 'd) scanner;;
(** {7:conversion Conversion specifications in format strings} *)
-(** Conversion specifications have the following form:
-
- [% \[flags\] \[width\] \[.precision\] type]
-
- In short, a conversion specification consists in the [%] character,
- followed by optional modifiers, and a type which is made of one or
- several characters.
-
- The types and their meanings are:
-
- - [d]: reads an optionally signed decimal integer.
- - [i]: reads an optionally signed integer
- (usual input conventions for decimal ([0-9]+), hexadecimal
- ([0x[0-9a-f]+] and [0X[0-9A-F]+]), octal ([0o[0-7]+]), and binary
- ([0b[0-1]+]) notations are understood).
- - [u]: reads an unsigned decimal integer.
- - [x] or [X]: reads an unsigned hexadecimal integer ([[0-9a-f]+] or [[0-9A-F]+]).
- - [o]: reads an unsigned octal integer ([[0-7]+]).
- - [s]: reads a string argument that spreads as much as possible, until
- the following bounding conditions holds:
- {ul
- {- a whitespace has been found (see {!Scanf.space}),}
- {- a scanning indication has been encountered
- (see scanning {!Scanf.indication}),}
- {- the end-of-input has been reached.}
- }
- Hence, the [%s] conversion always succeeds: it returns an empty
- string, if the bounding condition holds when the scan begins.
- - [S]: reads a delimited string argument (delimiters and special
- escaped characters follow the lexical conventions of OCaml).
- - [c]: reads a single character. To test the current input character
- without reading it, specify a null field width, i.e. use
- specification [%0c]. Raise [Invalid_argument], if the field width
- specification is greater than 1.
- - [C]: reads a single delimited character (delimiters and special
- escaped characters follow the lexical conventions of OCaml).
- - [f], [e], [E], [g], [G]: reads an optionally signed
- floating-point number in decimal notation, in the style [dddd.ddd
- e/E+-dd].
- - [F]: reads a floating point number according to the lexical
- conventions of OCaml (hence the decimal point is mandatory if the
- exponent part is not mentioned).
- - [B]: reads a boolean argument ([true] or [false]).
- - [b]: reads a boolean argument (for backward compatibility; do not use
- in new programs).
- - [ld], [li], [lu], [lx], [lX], [lo]: reads an [int32] argument to
- the format specified by the second letter for regular integers.
- - [nd], [ni], [nu], [nx], [nX], [no]: reads a [nativeint] argument to
- the format specified by the second letter for regular integers.
- - [Ld], [Li], [Lu], [Lx], [LX], [Lo]: reads an [int64] argument to
- the format specified by the second letter for regular integers.
- - [\[ range \]]: reads characters that matches one of the characters
- mentioned in the range of characters [range] (or not mentioned in
- it, if the range starts with [^]). Reads a [string] that can be
- empty, if the next input character does not match the range. The set of
- characters from [c1] to [c2] (inclusively) is denoted by [c1-c2].
- Hence, [%\[0-9\]] returns a string representing a decimal number
- or an empty string if no decimal digit is found; similarly,
- [%\[\\048-\\057\\065-\\070\]] returns a string of hexadecimal digits.
- If a closing bracket appears in a range, it must occur as the
- first character of the range (or just after the [^] in case of
- range negation); hence [\[\]\]] matches a [\]] character and
- [\[^\]\]] matches any character that is not [\]].
- - [r]: user-defined reader. Takes the next [ri] formatted input function and
- applies it to the scanning buffer [ib] to read the next argument. The
- input function [ri] must therefore have type [Scanning.in_channel -> 'a] and
- the argument read has type ['a].
- - [\{ fmt %\}]: reads a format string argument.
- The format string read must have the same type as the format string
- specification [fmt].
- For instance, ["%{ %i %}"] reads any format string that can read a value of
- type [int]; hence, if [s] is the string ["fmt:\"number is %u\""], then
- [Scanf.sscanf s "fmt: %{%i%}"] succeeds and returns the format string
- ["number is %u"].
- - [\( fmt %\)]: scanning format substitution.
- Reads a format string and then goes on scanning with the format string
- read, instead of using [fmt].
- The format string read must have the same type as the format string
- specification [fmt] that it replaces.
- For instance, ["%( %i %)"] reads any format string that can read a value
- of type [int].
- Returns the format string read, and the value read using the format
- string read.
- Hence, if [s] is the string ["\"%4d\"1234.00"], then
- [Scanf.sscanf s "%(%i%)" (fun fmt i -> fmt, i)] evaluates to
- [("%4d", 1234)].
- If the special flag [_] is used, the conversion discards the
- format string read and only returns the value read with the format
- string read.
- Hence, if [s] is the string ["\"%4d\"1234.00"], then
- [Scanf.sscanf s "%_(%i%)"] is simply equivalent to
- [Scanf.sscanf "1234.00" "%4d"].
- - [l]: returns the number of lines read so far.
- - [n]: returns the number of characters read so far.
- - [N] or [L]: returns the number of tokens read so far.
- - [!]: matches the end of input condition.
- - [%]: matches one [%] character in the input.
- - [,]: the no-op delimiter for conversion specifications.
-
- Following the [%] character that introduces a conversion, there may be
- the special flag [_]: the conversion that follows occurs as usual,
- but the resulting value is discarded.
- For instance, if [f] is the function [fun i -> i + 1], and [s] is the
- string ["x = 1"], then [Scanf.sscanf s "%_s = %i" f] returns [2].
-
- The optional [width] is an integer literal indicating the maximal width
- of the token to read.
- For instance, [%6d] reads an integer, having at most 6 decimal digits;
- [%4f] reads a float with at most 4 characters; and [%8\[\\000-\\255\]]
- returns the next 8 characters (or all the characters still available,
- if fewer than 8 characters are available in the input).
-
- The optional [precision] is a dot [.] followed by an integer literal
- indicating the maximum number of digits that follow the decimal point in
- the [%f], [%e], and [%E] conversions. For instance, [%.4f] reads a
- [float] with at most 4 fractional digits.
-
- Notes:
-
- - as mentioned above, the [%s] conversion always succeeds, even if there is
- nothing to read in the input: in this case, it simply returns [""].
-
- - in addition to the relevant digits, ['_'] characters may appear
- inside numbers (this is reminiscent to the usual OCaml lexical
- conventions). If stricter scanning is desired, use the range
- conversion facility instead of the number conversions.
-
- - the [scanf] facility is not intended for heavy duty lexical
- analysis and parsing. If it appears not expressive enough for your
- needs, several alternative exists: regular expressions (module
- [Str]), stream parsers, [ocamllex]-generated lexers,
- [ocamlyacc]-generated parsers. *)
+(** Conversion specifications consist in the [%] character, followed by
+ an optional flag, an optional field width, and followed by one or
+ two conversion characters. The conversion characters and their
+ meanings are:
+
+ - [d]: reads an optionally signed decimal integer.
+ - [i]: reads an optionally signed integer
+ (usual input conventions for decimal ([0-9]+), hexadecimal
+ ([0x[0-9a-f]+] and [0X[0-9A-F]+]), octal ([0o[0-7]+]), and binary
+ ([0b[0-1]+]) notations are understood).
+ - [u]: reads an unsigned decimal integer.
+ - [x] or [X]: reads an unsigned hexadecimal integer ([[0-9a-fA-F]+]).
+ - [o]: reads an unsigned octal integer ([[0-7]+]).
+ - [s]: reads a string argument that spreads as much as possible, until the
+ following bounding condition holds: {ul
+ {- a whitespace has been found (see {!Scanf.space}),}
+ {- a scanning indication (see scanning {!Scanf.indication}) has been
+ encountered,}
+ {- the end-of-input has been reached.}}
+ Hence, this conversion always succeeds: it returns an empty
+ string, if the bounding condition holds when the scan begins.
+ - [S]: reads a delimited string argument (delimiters and special
+ escaped characters follow the lexical conventions of Caml).
+ - [c]: reads a single character. To test the current input character
+ without reading it, specify a null field width, i.e. use
+ specification [%0c]. Raise [Invalid_argument], if the field width
+ specification is greater than 1.
+ - [C]: reads a single delimited character (delimiters and special
+ escaped characters follow the lexical conventions of Caml).
+ - [f], [e], [E], [g], [G]: reads an optionally signed
+ floating-point number in decimal notation, in the style [dddd.ddd
+ e/E+-dd].
+ - [F]: reads a floating point number according to the lexical
+ conventions of Caml (hence the decimal point is mandatory if the
+ exponent part is not mentioned).
+ - [B]: reads a boolean argument ([true] or [false]).
+ - [b]: reads a boolean argument (for backward compatibility; do not use
+ in new programs).
+ - [ld], [li], [lu], [lx], [lX], [lo]: reads an [int32] argument to
+ the format specified by the second letter for regular integers.
+ - [nd], [ni], [nu], [nx], [nX], [no]: reads a [nativeint] argument to
+ the format specified by the second letter for regular integers.
+ - [Ld], [Li], [Lu], [Lx], [LX], [Lo]: reads an [int64] argument to
+ the format specified by the second letter for regular integers.
+ - [\[ range \]]: reads characters that matches one of the characters
+ mentioned in the range of characters [range] (or not mentioned in
+ it, if the range starts with [^]). Reads a [string] that can be
+ empty, if the next input character does not match the range. The set of
+ characters from [c1] to [c2] (inclusively) is denoted by [c1-c2].
+ Hence, [%\[0-9\]] returns a string representing a decimal number
+ or an empty string if no decimal digit is found; similarly,
+ [%\[\\048-\\057\\065-\\070\]] returns a string of hexadecimal digits.
+ If a closing bracket appears in a range, it must occur as the
+ first character of the range (or just after the [^] in case of
+ range negation); hence [\[\]\]] matches a [\]] character and
+ [\[^\]\]] matches any character that is not [\]].
+ Use [%%] and [%\@] to include a [%] or a [\@] in a range.
+ - [r]: user-defined reader. Takes the next [ri] formatted input function and
+ applies it to the scanning buffer [ib] to read the next argument. The
+ input function [ri] must therefore have type [Scanning.in_channel -> 'a] and
+ the argument read has type ['a].
+ - [\{ fmt %\}]: reads a format string argument.
+ The format string read must have the same type as the format string
+ specification [fmt].
+ For instance, ["%{ %i %}"] reads any format string that can read a value of
+ type [int]; hence, if [s] is the string ["fmt:\"number is %u\""], then
+ [Scanf.sscanf s "fmt: %{%i%}"] succeeds and returns the format string
+ ["number is %u"].
+ - [\( fmt %\)]: scanning format substitution.
+ Reads a format string and then goes on scanning with the format string
+ read, instead of using [fmt].
+ The format string read must have the same type as the format string
+ specification [fmt] that it replaces.
+ For instance, ["%( %i %)"] reads any format string that can read a value
+ of type [int].
+ Returns the format string read, and the value read using the format
+ string read.
+ Hence, if [s] is the string ["\"%4d\"1234.00"], then
+ [Scanf.sscanf s "%(%i%)" (fun fmt i -> fmt, i)] evaluates to
+ [("%4d", 1234)].
+ If the special flag [_] is used, the conversion discards the
+ format string read and only returns the value read with the format
+ string read.
+ Hence, if [s] is the string ["\"%4d\"1234.00"], then
+ [Scanf.sscanf s "%_(%i%)"] is simply equivalent to
+ [Scanf.sscanf "1234.00" "%4d"].
+ - [l]: returns the number of lines read so far.
+ - [n]: returns the number of characters read so far.
+ - [N] or [L]: returns the number of tokens read so far.
+ - [!]: matches the end of input condition.
+ - [%]: matches one [%] character in the input.
+ - [\@]: matches one [\@] character in the input.
+ - [,]: does nothing.
+
+ Following the [%] character that introduces a conversion, there may be
+ the special flag [_]: the conversion that follows occurs as usual,
+ but the resulting value is discarded.
+ For instance, if [f] is the function [fun i -> i + 1], and [s] is the
+ string ["x = 1"], then [Scanf.sscanf s "%_s = %i" f] returns [2].
+
+ The field width is composed of an optional integer literal
+ indicating the maximal width of the token to read.
+ For instance, [%6d] reads an integer, having at most 6 decimal digits;
+ [%4f] reads a float with at most 4 characters; and [%8[\\000-\\255]]
+ returns the next 8 characters (or all the characters still available,
+ if fewer than 8 characters are available in the input).
+
+ Notes:
+
+ - as mentioned above, a [%s] conversion always succeeds, even if there is
+ nothing to read in the input: in this case, it simply returns [""].
+
+ - in addition to the relevant digits, ['_'] characters may appear
+ inside numbers (this is reminiscent to the usual Caml lexical
+ conventions). If stricter scanning is desired, use the range
+ conversion facility instead of the number conversions.
+
+ - the [scanf] facility is not intended for heavy duty lexical
+ analysis and parsing. If it appears not expressive enough for your
+ needs, several alternative exists: regular expressions (module
+ [Str]), stream parsers, [ocamllex]-generated lexers,
+ [ocamlyacc]-generated parsers. *)
(** {7:indication Scanning indications in format strings} *)
(** Scanning indications appear just after the string conversions [%s]
- and [%\[ range \]] to delimit the end of the token. A scanning
+ and [%[ range ]] to delimit the end of the token. A scanning
indication is introduced by a [\@] character, followed by some
- literal character [c]. It means that the string token should end
+ plain character [c]. It means that the string token should end
just before the next matching [c] (which is skipped). If no [c]
character is encountered, the string token spreads as much as
possible. For instance, ["%s@\t"] reads a string up to the next
- tab character or up to the end of input.
-
- When it does not introduce a scanning indication, the [\@] character
- introduces an escape for the next character: [\@c] is treated as a plain
- [c] character.
+ tab character or to the end of input. If a [\@] character appears
+ anywhere else in the format string, it is treated as a plain character.
Note:
- - the scanning indications introduce slight differences in the syntax of
+ - As usual in format strings, [%] characters must be escaped using [%%]
+ and [%\@] is equivalent to [\@]; this rule still holds within range
+ specifications and scanning indications.
+ For instance, ["%s@%%"] reads a string up to the next [%] character.
+ - The scanning indications introduce slight differences in the syntax of
[Scanf] format strings, compared to those used for the [Printf]
module. However, the scanning indications are similar to those used in
the [Format] module; hence, when producing formatted text to be scanned
@@ -513,10 +497,6 @@ val unescaped : string -> string
(** Return a copy of the argument with escape sequences, following the
lexical conventions of OCaml, replaced by their corresponding
special characters. If there is no escape sequence in the
- argument, still return a copy, contrary to String.escaped. *)
-
-(*
- Local Variables:
- compile-command: "cd ..; make world"
- End:
+ argument, still return a copy, contrary to String.escaped.
+ @since 3.13.0
*)
diff --git a/typing/typecore.ml b/typing/typecore.ml
index cac41a6f2..1db16e0c9 100644
--- a/typing/typecore.ml
+++ b/typing/typecore.ml
@@ -908,7 +908,7 @@ and is_nonexpansive_opt = function
(* Typing format strings for printing or reading.
- This format strings are used by functions in modules Printf, Format, and
+ These format strings are used by functions in modules Printf, Format, and
Scanf.
(Handling of * modifiers contributed by Thorsten Ohl.) *)
@@ -927,25 +927,6 @@ let type_format loc fmt =
let incomplete_format fmt =
raise (Error (loc, Incomplete_format fmt)) in
- let range_closing_index fmt i =
-
- let len = String.length fmt in
- let find_closing j =
- if j >= len then incomplete_format fmt else
- try String.index_from fmt j ']' with
- | Not_found -> incomplete_format fmt in
- let skip_pos j =
- if j >= len then incomplete_format fmt else
- match fmt.[j] with
- | ']' -> find_closing (j + 1)
- | c -> find_closing j in
- let rec skip_neg j =
- if j >= len then incomplete_format fmt else
- match fmt.[j] with
- | '^' -> skip_pos (j + 1)
- | c -> skip_pos j in
- find_closing (skip_neg (i + 1)) in
-
let rec type_in_format fmt =
let len = String.length fmt in
@@ -964,14 +945,7 @@ let type_format loc fmt =
else incomplete_format fmt else
match fmt.[i] with
| '%' -> scan_opts i (i + 1)
- | '@' -> skip_indication (i + 1)
| _ -> scan_format (i + 1)
- and skip_indication i =
- if i >= len then incomplete_format fmt else
- match fmt.[i] with
- | '@' | '%' -> scan_format (i + 1)
- | _ -> scan_format i
-
and scan_opts i j =
if j >= len then incomplete_format fmt else
match fmt.[j] with
@@ -1002,6 +976,48 @@ let type_format loc fmt =
match fmt.[j] with
| '.' -> scan_width_or_prec_value scan_conversion i (j + 1)
| _ -> scan_conversion i j
+ and scan_indication j =
+ if j >= len then j - 1 else
+ match fmt.[j] with
+ | '@' ->
+ let k = j + 1 in
+ if k >= len then j - 1 else
+ begin match fmt.[k] with
+ | '%' ->
+ let k = k + 1 in
+ if k >= len then j - 1 else
+ begin match fmt.[k] with
+ | '%' | '@' -> k
+ | _c -> j - 1
+ end
+ | _c -> k
+ end
+ | _c -> j - 1
+ and scan_range j =
+ let rec scan_closing j =
+ if j >= len then incomplete_format fmt else
+ match fmt.[j] with
+ | ']' -> j
+ | '%' ->
+ let j = j + 1 in
+ if j >= len then incomplete_format fmt else
+ begin match fmt.[j] with
+ | '%' | '@' -> scan_closing (j + 1)
+ | c -> bad_conversion fmt j c
+ end
+ | c -> scan_closing (j + 1) in
+ let scan_first_pos j =
+ if j >= len then incomplete_format fmt else
+ match fmt.[j] with
+ | ']' -> scan_closing (j + 1)
+ | c -> scan_closing j in
+ let rec scan_first_neg j =
+ if j >= len then incomplete_format fmt else
+ match fmt.[j] with
+ | '^' -> scan_first_pos (j + 1)
+ | c -> scan_first_pos j in
+
+ scan_first_neg j
and conversion j ty_arg =
let ty_uresult, ty_result = scan_format (j + 1) in
@@ -1021,13 +1037,16 @@ let type_format loc fmt =
and scan_conversion i j =
if j >= len then incomplete_format fmt else
match fmt.[j] with
- | '%' | '!' | ',' -> scan_format (j + 1)
- | 's' | 'S' -> conversion j Predef.type_string
+ | '%' | '@' | '!' | ',' -> scan_format (j + 1)
+ | 's' | 'S' ->
+ let j = scan_indication (j + 1) in
+ conversion j Predef.type_string
| '[' ->
- let j = range_closing_index fmt j in
+ let j = scan_range (j + 1) in
+ let j = scan_indication (j + 1) in
conversion j Predef.type_string
| 'c' | 'C' -> conversion j Predef.type_char
- | 'd' | 'i' | 'o' | 'x' | 'X' | 'u' | 'N' ->
+ | 'd' | 'i' | 'o' | 'u' | 'x' | 'X' | 'N' ->
conversion j Predef.type_int
| 'f' | 'e' | 'E' | 'g' | 'G' | 'F' -> conversion j Predef.type_float
| 'B' | 'b' -> conversion j Predef.type_bool
@@ -1056,7 +1075,7 @@ let type_format loc fmt =
let j = j + 1 in
if j >= len then conversion (j - 1) Predef.type_int else begin
match fmt.[j] with
- | 'd' | 'i' | 'o' | 'x' | 'X' | 'u' ->
+ | 'd' | 'i' | 'o' | 'u' | 'x' | 'X' ->
let ty_arg =
match c with
| 'l' -> Predef.type_int32
@@ -1085,9 +1104,10 @@ let type_format loc fmt =
let ty_ureader, ty_args = scan_format 0 in
newty
(Tconstr
- (Predef.path_format6,
- [ty_args; ty_input; ty_aresult; ty_ureader; ty_uresult; ty_result],
- ref Mnil)) in
+ (Predef.path_format6,
+ [ ty_args; ty_input; ty_aresult;
+ ty_ureader; ty_uresult; ty_result; ],
+ ref Mnil)) in
type_in_format fmt
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-03-27 15:49:16 +0000