core :: Text :: _hash_cache
core :: Text :: apply_format
core :: Text :: binarydigest_to_bytes
Return aBytes
by reading 0 and 1.
core :: Text :: capitalized
Returns a capitalizedself
core :: Text :: chars_to_escape_csv
How many more bytes should be allocated for CSV escaping ?core :: Text :: chars_to_unescape_csv
How many bytes should be removed for CSV unescaping ?core :: Text :: copy_to_native
Copiesn
bytes from self
at src_offset
into dest
starting at dest_offset
core :: Text :: decode_base64
Decodes the receiver string to base64 using a custom padding character.core :: Text :: defaultinit
core :: Text :: deserialize_json
Deserialize anullable Object
from this JSON formatted string
core :: Text :: encode_base64
Encodes the receiver string to base64 using a custom padding character.core :: Text :: english_scoring
Scoreself
according to english's letter frequency.
core :: Text :: escape_more_to_c
Escape additionnal characterscore :: Text :: escape_to_c
Escape"
\
'
, trigraphs and non printable characters using the rules of literal C strings and characters
core :: Text :: escape_to_csv
Escape the content ofself
for inclusion in a CSV document
core :: Text :: escape_to_gettext
core :: Text :: escape_to_js
Escape the content ofself
to pass to JavaScript code
core :: Text :: escape_to_utf16
Returnsself
with all characters escaped with their UTF-16 representation
core :: Text :: file_extension
Return right-most extension (without the dot)core :: Text :: file_lstat
The status of a file or of a symlink. see POSIX lstat(2).core :: Text :: from_percent_encoding
Decodeself
from percent (or URL) encoding to a clear string
core :: Text :: from_utf16_digit
Returns a UTF-16 escape valuecore :: Text :: from_utf16_escape
Returns the Unicode char escaped byself
core :: Text :: get_numext
Gets the numeric extension (i/u 8/16/32) inself
is present
core :: Text :: group_exists
Does the operating system know the group namedself
?
core :: Text :: has_substring
Does self have a substringstr
starting from position pos
?
core :: Text :: hash_cache
core :: Text :: hash_cache=
core :: Text :: hexdigest_to_bytes
Returns a newBytes
instance with the digest as content
core :: Text :: html_escape
Escape the characters<
, >
, &
, "
, '
and /
as HTML/XML entity references.
core :: Text :: html_link_prefixes
core :: Text :: http_download
Download the file at URLself
to output_path
with a simple HTTP request
self
core :: Text :: index_of_from
Gets the index of the first occurence of ´c´ starting from ´pos´core :: Text :: internal_to_dot
Writes self as a dot file on the hard drivecore :: Text :: is_numeric
Is this string in a valid numeric format compatible withto_f
?
core :: Text :: is_valid_html_tag
core :: Text :: is_whitespace
Is the string non-empty but only made of whitespaces?core :: Text :: json_need_escape
Doesself
need treatment from JSON to Nit ?
core :: Text :: json_to_nit_string
Escapesself
from a JSON string to a Nit string
core :: Text :: last_index_of_from
The index of the last occurrence of an element starting from pos (in reverse order).core :: Text :: levenshtein_distance
Return the Levenshtein distance between two stringscore :: Text :: light_gray
Make the text appear in light gray (or white) in a ANSI/VT100 terminal.core :: Text :: meta_from_fence
Extract string found at end of fence opening.core :: Text :: parse_bmfont
Parseself
as an XML BMFont description file
core :: Text :: read_md_link
Read a markdown link address and append it to theout
buffer.
core :: Text :: read_md_link_id
Read a markdown link text and append it to theout
buffer.
core :: Text :: read_raw_until
Readself
as raw text until nend
and append it to the out
buffer.
core :: Text :: read_until
Readself
until nend
and append it to the out
buffer.
core :: Text :: read_until
Readself
as raw text until nend
and append it to the out
buffer.
core :: Text :: read_xml_until
Readself
as XML until to
and append it to the out
buffer.
core :: Text :: remove_all
Returns a copy ofself
minus all occurences of pattern
core :: Text :: replace_first
Replace the first occurrence ofpattern
with string
core :: Text :: run_js_native
core :: Text :: search_all
Search all occurrences ofpattern
into self.
core :: Text :: search_from
Search the first occurence ofpattern
after from
.
core :: Text :: search_last
Search the last occurence of the textt
.
core :: Text :: search_last_up_to
Search the last occurence of the textt
before up_to
.
core :: Text :: simplify_path
Simplify a file path by remove useless.
, removing //
, and resolving ..
core :: Text :: skip_spaces
Get the position of the next non-space character.core :: Text :: split_once_on
Splitself
on the first occurence of pattern
core :: Text :: split_with
@deprecated alias forsplit
core :: Text :: strip_extension
Remove the trailingextension
.
core :: Text :: strip_nullable
Strip thenullable
prefix from the type name self
core :: Text :: strip_nullable_and_params
Strip thenullable
prefix and the params from the type name self
core :: Text :: strip_numext
Removes the numeric extension if presentcore :: Text :: strip_numhead
Removes the numeric head ofself
if present
core :: Text :: substring_from
Create a substring fromself
beginning at the from
position
core :: Text :: substrings
Iterates on the substrings of self if anycore :: Text :: to_camel_case
Takes a snake caseself
and converts it to camel case
core :: Text :: to_cmangle
Mangle a string to be a unique string only made of alphanumeric characters and underscores.core :: Text :: to_percent_encoding
Encodeself
to percent (or URL) encoding
core :: Text :: to_program_name
Convert the path (self
) to a program name.
core :: Text :: to_snake_case
Takes a camel caseself
and converts it to snake case
core :: Text :: to_sql_date_string
Format the date represented byself
into an escaped string for SQLite
core :: Text :: unescape_csv
Unescape the content ofself
from CSV format to Nit String
core :: Text :: unescape_json
Removes JSON-escaping if necessary in a JSON stringcore :: Text :: unescape_nit
Return a string where Nit escape sequences are transformed.core :: Text :: unescape_to_bytes
Return aBytes
instance where Nit escape sequences are transformed.
core :: Text :: user_exists
Does the operating system know the user namedself
?
core :: Text :: write_native_to
serialization :: inspect $ Text :: accept_inspect_serializer
json :: serialization_write $ Text :: accept_json_serializer
Refinable service to customize the serialization of this class to JSONmsgpack :: serialization_write $ Text :: accept_msgpack_serializer
Hook to customize the serialization of this class to MessagePackandroid :: http_request $ Text :: http_get
Execute an HTTP GET request synchronously at the URIself
ios :: http_request $ Text :: http_get
Execute an HTTP GET request synchronously at the URIself
linux :: http_request $ Text :: http_get
Execute an HTTP GET request synchronously at the URIself
ios :: ui $ Text :: open_in_browser
Open the URLself
with the default browser
android :: ui $ Text :: open_in_browser
Open the URLself
with the default browser
linux :: ui $ Text :: open_in_browser
Open the URLself
with the default browser
core :: string_search $ Text :: search_index_in
Searchself
into s
from a certain position.
core :: Text :: _hash_cache
serialization :: Serializable :: accept_inspect_serializer_core
serialization :: Serializable :: accept_json_serializer
Refinable service to customize the serialization of this class to JSONserialization :: Serializable :: accept_msgpack_attribute_counter
Hook to customize the behavior of theAttributeCounter
serialization :: Serializable :: accept_msgpack_serializer
Hook to customize the serialization of this class to MessagePackserialization :: Serializable :: add_to_bundle
Called by[]=
to dynamically choose the appropriate method according
core :: Text :: apply_format
core :: Text :: binarydigest_to_bytes
Return aBytes
by reading 0 and 1.
core :: Text :: capitalized
Returns a capitalizedself
core :: Text :: chars_to_escape_csv
How many more bytes should be allocated for CSV escaping ?core :: Text :: chars_to_unescape_csv
How many bytes should be removed for CSV unescaping ?core :: Object :: class_factory
Implementation used byget_class
to create the specific class.
core :: Text :: copy_to_native
Copiesn
bytes from self
at src_offset
into dest
starting at dest_offset
serialization :: Serializable :: core_serialize_to
Actual serialization ofself
to serializer
core :: Text :: decode_base64
Decodes the receiver string to base64 using a custom padding character.core :: Object :: defaultinit
core :: Text :: defaultinit
mpi :: Sendable :: defaultinit
core :: Writable :: defaultinit
core :: Pattern :: defaultinit
core :: Cloneable :: defaultinit
core :: Comparable :: defaultinit
core :: Text :: deserialize_json
Deserialize anullable Object
from this JSON formatted string
core :: Text :: encode_base64
Encodes the receiver string to base64 using a custom padding character.core :: Text :: english_scoring
Scoreself
according to english's letter frequency.
core :: Text :: escape_more_to_c
Escape additionnal characterscore :: Text :: escape_to_c
Escape"
\
'
, trigraphs and non printable characters using the rules of literal C strings and characters
core :: Text :: escape_to_csv
Escape the content ofself
for inclusion in a CSV document
core :: Text :: escape_to_gettext
core :: Text :: escape_to_js
Escape the content ofself
to pass to JavaScript code
core :: Text :: escape_to_utf16
Returnsself
with all characters escaped with their UTF-16 representation
core :: Text :: file_extension
Return right-most extension (without the dot)core :: Text :: file_lstat
The status of a file or of a symlink. see POSIX lstat(2).serialization :: Serializable :: from_deserializer
Create an instance of this class from thedeserializer
core :: Text :: from_percent_encoding
Decodeself
from percent (or URL) encoding to a clear string
core :: Text :: from_utf16_digit
Returns a UTF-16 escape valuecore :: Text :: from_utf16_escape
Returns the Unicode char escaped byself
core :: Text :: get_numext
Gets the numeric extension (i/u 8/16/32) inself
is present
core :: Text :: group_exists
Does the operating system know the group namedself
?
core :: Text :: has_substring
Does self have a substringstr
starting from position pos
?
core :: Text :: hash_cache
core :: Text :: hash_cache=
core :: Text :: hexdigest_to_bytes
Returns a newBytes
instance with the digest as content
core :: Text :: html_escape
Escape the characters<
, >
, &
, "
, '
and /
as HTML/XML entity references.
core :: Text :: html_link_prefixes
core :: Text :: http_download
Download the file at URLself
to output_path
with a simple HTTP request
self
core :: Text :: index_of_from
Gets the index of the first occurence of ´c´ starting from ´pos´core :: Text :: internal_to_dot
Writes self as a dot file on the hard drivecore :: Text :: is_numeric
Is this string in a valid numeric format compatible withto_f
?
core :: Object :: is_same_instance
Return true ifself
and other
are the same instance (i.e. same identity).
core :: Object :: is_same_serialized
Isself
the same as other
in a serialization context?
core :: Object :: is_same_type
Return true ifself
and other
have the same dynamic type.
core :: Text :: is_valid_html_tag
core :: Text :: is_whitespace
Is the string non-empty but only made of whitespaces?core :: Text :: json_need_escape
Doesself
need treatment from JSON to Nit ?
core :: Text :: json_to_nit_string
Escapesself
from a JSON string to a Nit string
core :: Text :: last_index_of_from
The index of the last occurrence of an element starting from pos (in reverse order).core :: Text :: levenshtein_distance
Return the Levenshtein distance between two stringscore :: Text :: light_gray
Make the text appear in light gray (or white) in a ANSI/VT100 terminal.core :: Text :: meta_from_fence
Extract string found at end of fence opening.serialization :: Serializable :: msgpack_extra_array_items
Hook to request a larger than usual metadata arraycore :: Object :: native_class_name
The class name of the object in CString format.core :: Object :: output_class_name
Display class name on stdout (debug only).core :: Text :: parse_bmfont
Parseself
as an XML BMFont description file
core :: Text :: read_md_link
Read a markdown link address and append it to theout
buffer.
core :: Text :: read_md_link_id
Read a markdown link text and append it to theout
buffer.
core :: Text :: read_raw_until
Readself
as raw text until nend
and append it to the out
buffer.
core :: Text :: read_until
Readself
until nend
and append it to the out
buffer.
core :: Text :: read_until
Readself
as raw text until nend
and append it to the out
buffer.
core :: Text :: read_xml_until
Readself
as XML until to
and append it to the out
buffer.
core :: Text :: remove_all
Returns a copy ofself
minus all occurences of pattern
core :: Text :: replace_first
Replace the first occurrence ofpattern
with string
core :: Text :: run_js_native
core :: Text :: search_all
Search all occurrences ofpattern
into self.
core :: Pattern :: search_all_in
Search allself
occurrences into s
.
core :: Text :: search_from
Search the first occurence ofpattern
after from
.
core :: Pattern :: search_index_in
Searchself
into s
from a certain position.
core :: Text :: search_last
Search the last occurence of the textt
.
core :: Text :: search_last_up_to
Search the last occurence of the textt
before up_to
.
serialization :: Serializable :: serialize_msgpack
Serializeself
to MessagePack bytes
serialization :: Serializable :: serialize_to
Serializeself
to serializer
serialization :: Serializable :: serialize_to_json
Serializeself
to JSON
serialization :: Serializable :: serialize_to_or_delay
Accept references or force direct serialization (usingserialize_to
)
core :: Text :: simplify_path
Simplify a file path by remove useless.
, removing //
, and resolving ..
core :: Text :: skip_spaces
Get the position of the next non-space character.core :: Text :: split_once_on
Splitself
on the first occurence of pattern
core :: Text :: split_with
@deprecated alias forsplit
core :: Text :: strip_extension
Remove the trailingextension
.
core :: Text :: strip_nullable
Strip thenullable
prefix from the type name self
core :: Text :: strip_nullable_and_params
Strip thenullable
prefix and the params from the type name self
core :: Text :: strip_numext
Removes the numeric extension if presentcore :: Text :: strip_numhead
Removes the numeric head ofself
if present
core :: Text :: substring_from
Create a substring fromself
beginning at the from
position
core :: Text :: substrings
Iterates on the substrings of self if anycore :: Text :: to_camel_case
Takes a snake caseself
and converts it to camel case
core :: Text :: to_cmangle
Mangle a string to be a unique string only made of alphanumeric characters and underscores.core :: Text :: to_percent_encoding
Encodeself
to percent (or URL) encoding
serialization :: Serializable :: to_pretty_json
Serializeself
to plain pretty JSON
core :: Text :: to_program_name
Convert the path (self
) to a program name.
core :: Text :: to_snake_case
Takes a camel caseself
and converts it to snake case
core :: Text :: to_sql_date_string
Format the date represented byself
into an escaped string for SQLite
core :: Text :: unescape_csv
Unescape the content ofself
from CSV format to Nit String
core :: Text :: unescape_json
Removes JSON-escaping if necessary in a JSON stringcore :: Text :: unescape_nit
Return a string where Nit escape sequences are transformed.core :: Text :: unescape_to_bytes
Return aBytes
instance where Nit escape sequences are transformed.
core :: Text :: user_exists
Does the operating system know the user namedself
?
core :: Text :: write_native_to
core :: Writable :: write_to_bytes
Likewrite_to
but return a new Bytes (may be quite large)
core :: Writable :: write_to_file
Likewrite_to
but take care of creating the file
core :: Writable :: write_to_string
Likewrite_to
but return a new String (may be quite large).
Serializer::serialize
serialization :: DirectSerializable
Instances of this class are not delayed and instead serialized immediately
# High-level abstraction for all text representations
abstract class Text
super Comparable
super Cloneable
redef type OTHER: Text
# Type of self (used for factorization of several methods, ex : substring_from, empty...)
type SELFTYPE: Text
# Gets a view on the chars of the Text object
#
# ~~~
# assert "hello".chars.to_a == ['h', 'e', 'l', 'l', 'o']
# ~~~
fun chars: SequenceRead[Char] is abstract
# Gets a view on the bytes of the Text object
#
# ~~~
# assert "hello".bytes.to_a == [104, 101, 108, 108, 111]
# ~~~
fun bytes: SequenceRead[Int] is abstract
# Number of characters contained in self.
#
# ~~~
# assert "12345".length == 5
# assert "".length == 0
# assert "あいうえお".length == 5
# ~~~
fun length: Int is abstract
# Number of bytes in `self`
#
# ~~~
# assert "12345".byte_length == 5
# assert "あいうえお".byte_length == 15
# ~~~
fun byte_length: Int is abstract
# Create a substring.
#
# ~~~
# assert "abcd".substring(1, 2) == "bc"
# assert "abcd".substring(-1, 2) == "a"
# assert "abcd".substring(1, 0) == ""
# assert "abcd".substring(2, 5) == "cd"
# assert "あいうえお".substring(1,3) == "いうえ"
# ~~~
#
# A `from` index < 0 will be replaced by 0.
# Unless a `count` value is > 0 at the same time.
# In this case, `from += count` and `count -= from`.
fun substring(from: Int, count: Int): SELFTYPE is abstract
# Iterates on the substrings of self if any
private fun substrings: Iterator[FlatText] is abstract
# Is the current Text empty (== "")
#
# ~~~
# assert "".is_empty
# assert not "foo".is_empty
# ~~~
fun is_empty: Bool do return self.length == 0
# Returns an empty Text of the right type
#
# This method is used internally to get the right
# implementation of an empty string.
protected fun empty: SELFTYPE is abstract
# Returns a copy of `self` as a Buffer
fun to_buffer: Buffer is abstract
# Gets the first char of the Text
fun first: Char do return self.chars[0]
# Access a character at `index` in the string.
#
# ~~~
# assert "abcd"[2] == 'c'
# ~~~
fun [](index: Int): Char do return self.chars[index]
# Gets the index of the first occurence of 'c'
#
# Returns -1 if not found
fun index_of(c: Char): Int
do
return index_of_from(c, 0)
end
# Gets the last char of self
fun last: Char do return self.chars[length-1]
# Gets the index of the first occurence of ´c´ starting from ´pos´
#
# Returns -1 if not found
fun index_of_from(c: Char, pos: Int): Int
do
var iter = self.chars.iterator_from(pos)
while iter.is_ok do
if iter.item == c then return iter.index
iter.next
end
return -1
end
# Gets the last index of char ´c´
#
# Returns -1 if not found
fun last_index_of(c: Char): Int
do
return last_index_of_from(c, length - 1)
end
# Return a null terminated char *
fun to_cstring: CString is abstract
# The index of the last occurrence of an element starting from pos (in reverse order).
#
# ~~~
# var s = "/etc/bin/test/test.nit"
# assert s.last_index_of_from('/', s.length-1) == 13
# assert s.last_index_of_from('/', 12) == 8
# ~~~
#
# Returns -1 if not found
fun last_index_of_from(item: Char, pos: Int): Int do return chars.last_index_of_from(item, pos)
# Concatenates `o` to `self`
#
# ~~~
# assert "hello" + "world" == "helloworld"
# assert "" + "hello" + "" == "hello"
# ~~~
fun +(o: Text): SELFTYPE is abstract
# Gets an iterator on the chars of self
fun iterator: Iterator[Char]
do
return self.chars.iterator
end
# Gets an Array containing the chars of self
fun to_a: Array[Char] do return chars.to_a
# Create a substring from `self` beginning at the `from` position
#
# ~~~
# assert "abcd".substring_from(1) == "bcd"
# assert "abcd".substring_from(-1) == "abcd"
# assert "abcd".substring_from(2) == "cd"
# ~~~
#
# As with substring, a `from` index < 0 will be replaced by 0
fun substring_from(from: Int): SELFTYPE
do
if from >= self.length then return empty
if from < 0 then from = 0
return substring(from, length - from)
end
# Does self have a substring `str` starting from position `pos`?
#
# ~~~
# assert "abcd".has_substring("bc",1) == true
# assert "abcd".has_substring("bc",2) == false
# ~~~
#
# Returns true iff all characters of `str` are presents
# at the expected index in `self.`
# The first character of `str` being at `pos`, the second
# character being at `pos+1` and so on...
#
# This means that all characters of `str` need to be inside `self`.
#
# ~~~
# assert "abcd".has_substring("xab", -1) == false
# assert "abcd".has_substring("cdx", 2) == false
# ~~~
#
# And that the empty string is always a valid substring.
#
# ~~~
# assert "abcd".has_substring("", 2) == true
# assert "abcd".has_substring("", 200) == true
# ~~~
fun has_substring(str: String, pos: Int): Bool
do
if str.is_empty then return true
if pos < 0 or pos + str.length > length then return false
var myiter = self.chars.iterator_from(pos)
var itsiter = str.chars.iterator
while myiter.is_ok and itsiter.is_ok do
if myiter.item != itsiter.item then return false
myiter.next
itsiter.next
end
if itsiter.is_ok then return false
return true
end
# Is this string prefixed by `prefix`?
#
# ~~~
# assert "abcd".has_prefix("ab") == true
# assert "abcbc".has_prefix("bc") == false
# assert "ab".has_prefix("abcd") == false
# ~~~
fun has_prefix(prefix: String): Bool do return has_substring(prefix,0)
# Is this string suffixed by `suffix`?
#
# ~~~
# assert "abcd".has_suffix("abc") == false
# assert "abcd".has_suffix("bcd") == true
# ~~~
fun has_suffix(suffix: String): Bool do return has_substring(suffix, length - suffix.length)
# Returns `self` as the corresponding integer
#
# ~~~
# assert "123".to_i == 123
# assert "-1".to_i == -1
# assert "0x64".to_i == 100
# assert "0b1100_0011".to_i== 195
# assert "--12".to_i == 12
# assert "+45".to_i == 45
# ~~~
#
# REQUIRE: `self`.`is_int`
fun to_i: Int is abstract
# If `self` contains a float, return the corresponding float
#
# ~~~
# assert "123".to_f == 123.0
# assert "-1".to_f == -1.0
# assert "-1.2e-3".to_f == -0.0012
# ~~~
fun to_f: Float
do
# Shortcut
return to_s.to_cstring.atof
end
# If `self` contains only digits and alpha <= 'f', return the corresponding integer.
#
# ~~~
# assert "ff".to_hex == 255
# ~~~
fun to_hex(pos, ln: nullable Int): Int do
var res = 0
if pos == null then pos = 0
if ln == null then ln = length - pos
var max = pos + ln
for i in [pos .. max[ do
res <<= 4
res += self[i].from_hex
end
return res
end
# If `self` contains only digits <= '7', return the corresponding integer.
#
# ~~~
# assert "714".to_oct == 460
# ~~~
fun to_oct: Int do return a_to(8)
# If `self` contains only '0' et '1', return the corresponding integer.
#
# ~~~
# assert "101101".to_bin == 45
# ~~~
fun to_bin: Int do return a_to(2)
# If `self` contains only digits '0' .. '9', return the corresponding integer.
#
# ~~~
# assert "108".to_dec == 108
# ~~~
fun to_dec: Int do return a_to(10)
# If `self` contains only digits and letters, return the corresponding integer in a given base
#
# ~~~
# assert "120".a_to(3) == 15
# ~~~
fun a_to(base: Int) : Int
do
var i = 0
var neg = false
for j in [0..length[ do
var c = chars[j]
var v = c.to_i
if v > base then
if neg then
return -i
else
return i
end
else if v < 0 then
neg = true
else
i = i * base + v
end
end
if neg then
return -i
else
return i
end
end
# Is this string in a valid numeric format compatible with `to_f`?
#
# ~~~
# assert "123".is_numeric == true
# assert "1.2".is_numeric == true
# assert "-1.2".is_numeric == true
# assert "-1.23e-2".is_numeric == true
# assert "1..2".is_numeric == false
# assert "".is_numeric == false
# ~~~
fun is_numeric: Bool
do
var has_point = false
var e_index = -1
for i in [0..length[ do
var c = chars[i]
if not c.is_numeric then
if c == '.' and not has_point then
has_point = true
else if c == 'e' and e_index == -1 and i > 0 and i < length - 1 and chars[i-1] != '-' then
e_index = i
else if c == '-' and i == e_index + 1 and i < length - 1 then
else
return false
end
end
end
return not is_empty
end
# Returns `true` if the string contains only Hex chars
#
# ~~~
# assert "048bf".is_hex == true
# assert "ABCDEF".is_hex == true
# assert "0G".is_hex == false
# ~~~
fun is_hex: Bool
do
for i in [0..length[ do
var c = chars[i]
if not (c >= 'a' and c <= 'f') and
not (c >= 'A' and c <= 'F') and
not (c >= '0' and c <= '9') then return false
end
return true
end
# Returns `true` if the string contains only Binary digits
#
# ~~~
# assert "1101100".is_bin == true
# assert "1101020".is_bin == false
# ~~~
fun is_bin: Bool do
for i in chars do if i != '0' and i != '1' then return false
return true
end
# Returns `true` if the string contains only Octal digits
#
# ~~~
# assert "213453".is_oct == true
# assert "781".is_oct == false
# ~~~
fun is_oct: Bool do
for i in chars do if i < '0' or i > '7' then return false
return true
end
# Returns `true` if the string contains only Decimal digits
#
# ~~~
# assert "10839".is_dec == true
# assert "164F".is_dec == false
# ~~~
fun is_dec: Bool do
for i in chars do if i < '0' or i > '9' then return false
return true
end
# Are all letters in `self` upper-case ?
#
# ~~~
# assert "HELLO WORLD".is_upper == true
# assert "%$&%!".is_upper == true
# assert "hello world".is_upper == false
# assert "Hello World".is_upper == false
# ~~~
fun is_upper: Bool
do
for i in [0..length[ do
var char = chars[i]
if char.is_lower then return false
end
return true
end
# Are all letters in `self` lower-case ?
#
# ~~~
# assert "hello world".is_lower == true
# assert "%$&%!".is_lower == true
# assert "Hello World".is_lower == false
# ~~~
fun is_lower: Bool
do
for i in [0..length[ do
var char = chars[i]
if char.is_upper then return false
end
return true
end
# Removes the whitespaces at the beginning of self
#
# ~~~
# assert " \n\thello \n\t".l_trim == "hello \n\t"
# ~~~
#
# `Char::is_whitespace` determines what is a whitespace.
fun l_trim: SELFTYPE
do
var iter = self.chars.iterator
while iter.is_ok do
if not iter.item.is_whitespace then break
iter.next
end
if iter.index == length then return self.empty
return self.substring_from(iter.index)
end
# Removes the whitespaces at the end of self
#
# ~~~
# assert " \n\thello \n\t".r_trim == " \n\thello"
# ~~~
#
# `Char::is_whitespace` determines what is a whitespace.
fun r_trim: SELFTYPE
do
var iter = self.chars.reverse_iterator
while iter.is_ok do
if not iter.item.is_whitespace then break
iter.next
end
if iter.index < 0 then return self.empty
return self.substring(0, iter.index + 1)
end
# Trims trailing and preceding white spaces
#
# ~~~
# assert " Hello World ! ".trim == "Hello World !"
# assert "\na\nb\tc\t".trim == "a\nb\tc"
# ~~~
#
# `Char::is_whitespace` determines what is a whitespace.
fun trim: SELFTYPE do return (self.l_trim).r_trim
# Is the string non-empty but only made of whitespaces?
#
# ~~~
# assert " \n\t ".is_whitespace == true
# assert " hello ".is_whitespace == false
# assert "".is_whitespace == false
# ~~~
#
# `Char::is_whitespace` determines what is a whitespace.
fun is_whitespace: Bool
do
if is_empty then return false
for c in self.chars do
if not c.is_whitespace then return false
end
return true
end
# Returns `self` removed from its last line terminator (if any).
#
# ~~~
# assert "Hello\n".chomp == "Hello"
# assert "Hello".chomp == "Hello"
#
# assert "\n".chomp == ""
# assert "".chomp == ""
# ~~~
#
# Line terminators are `"\n"`, `"\r\n"` and `"\r"`.
# A single line terminator, the last one, is removed.
#
# ~~~
# assert "\r\n".chomp == ""
# assert "\r\n\n".chomp == "\r\n"
# assert "\r\n\r\n".chomp == "\r\n"
# assert "\r\n\r".chomp == "\r\n"
# ~~~
#
# Note: unlike with most IO methods like `Reader::read_line`,
# a single `\r` is considered here to be a line terminator and will be removed.
fun chomp: SELFTYPE
do
var len = length
if len == 0 then return self
var l = self.chars.last
if l == '\r' then
return substring(0, len-1)
else if l != '\n' then
return self
else if len > 1 and self.chars[len-2] == '\r' then
return substring(0, len-2)
else
return substring(0, len-1)
end
end
# Justify `self` in a space of `length`
#
# `left` is the space ratio on the left side.
# * 0.0 for left-justified (no space at the left)
# * 1.0 for right-justified (all spaces at the left)
# * 0.5 for centered (half the spaces at the left)
#
# `char`, or `' '` by default, is repeated to pad the empty space.
#
# Examples
#
# ~~~
# assert "hello".justify(10, 0.0) == "hello "
# assert "hello".justify(10, 1.0) == " hello"
# assert "hello".justify(10, 0.5) == " hello "
# assert "hello".justify(10, 0.5, '.') == "..hello..."
# ~~~
#
# If `length` is not enough, `self` is returned as is.
#
# ~~~
# assert "hello".justify(2, 0.0) == "hello"
# ~~~
#
# REQUIRE: `left >= 0.0 and left <= 1.0`
# ENSURE: `self.length <= length implies result.length == length`
# ENSURE: `self.length >= length implies result == self`
fun justify(length: Int, left: Float, char: nullable Char): String
do
var pad = (char or else ' ').to_s
var diff = length - self.length
if diff <= 0 then return to_s
assert left >= 0.0 and left <= 1.0
var before = (diff.to_f * left).to_i
return pad * before + self + pad * (diff-before)
end
# Mangle a string to be a unique string only made of alphanumeric characters and underscores.
#
# This method is injective (two different inputs never produce the same
# output) and the returned string always respect the following rules:
#
# * Contains only US-ASCII letters, digits and underscores.
# * Never starts with a digit.
# * Never ends with an underscore.
# * Never contains two contiguous underscores.
#
# Examples:
#
# ~~~
# assert "42_is/The answer!".to_cmangle == "_52d2_is_47dThe_32danswer_33d"
# assert "__".to_cmangle == "_95d_95d"
# assert "__d".to_cmangle == "_95d_d"
# assert "_d_".to_cmangle == "_d_95d"
# assert "_42".to_cmangle == "_95d42"
# assert "foo".to_cmangle == "foo"
# assert "".to_cmangle == ""
# ~~~
fun to_cmangle: String
do
if is_empty then return ""
var res = new Buffer
var underscore = false
var start = 0
var c = self[0]
if c >= '0' and c <= '9' then
res.add('_')
res.append(c.code_point.to_s)
res.add('d')
start = 1
end
for i in [start..length[ do
c = self[i]
if (c >= 'a' and c <= 'z') or (c >='A' and c <= 'Z') then
res.add(c)
underscore = false
continue
end
if underscore then
res.append('_'.code_point.to_s)
res.add('d')
end
if c >= '0' and c <= '9' then
res.add(c)
underscore = false
else if c == '_' then
res.add(c)
underscore = true
else
res.add('_')
res.append(c.code_point.to_s)
res.add('d')
underscore = false
end
end
if underscore then
res.append('_'.code_point.to_s)
res.add('d')
end
return res.to_s
end
# Escape `"` `\` `'`, trigraphs and non printable characters using the rules of literal C strings and characters
#
# ~~~
# assert "abAB12<>&".escape_to_c == "abAB12<>&"
# assert "\n\"'\\".escape_to_c == "\\n\\\"\\'\\\\"
# assert "allo???!".escape_to_c == "allo??\\?!"
# assert "??=??/??'??(??)".escape_to_c == "?\\?=?\\?/??\\'?\\?(?\\?)"
# assert "??!??<??>??-".escape_to_c == "?\\?!?\\?<?\\?>?\\?-"
# ~~~
#
# Most non-printable characters (bellow ASCII 32) are escaped to an octal form `\nnn`.
# Three digits are always used to avoid following digits to be interpreted as an element
# of the octal sequence.
#
# ~~~
# assert "{0.code_point}{1.code_point}{8.code_point}{31.code_point}{32.code_point}".escape_to_c == "\\000\\001\\010\\037 "
# ~~~
#
# The exceptions are the common `\t` and `\n`.
fun escape_to_c: String
do
var b = new Buffer
for i in [0..length[ do
var c = chars[i]
if c == '\n' then
b.append("\\n")
else if c == '\t' then
b.append("\\t")
else if c == '"' then
b.append("\\\"")
else if c == '\'' then
b.append("\\\'")
else if c == '\\' then
b.append("\\\\")
else if c == '?' then
# Escape if it is the last question mark of a ANSI C trigraph.
var j = i + 1
if j < length then
var next = chars[j]
# We ignore `??'` because it will be escaped as `??\'`.
if
next == '!' or
next == '(' or
next == ')' or
next == '-' or
next == '/' or
next == '<' or
next == '=' or
next == '>'
then b.add('\\')
end
b.add('?')
else if c.code_point < 32 then
b.add('\\')
var oct = c.code_point.to_base(8)
# Force 3 octal digits since it is the
# maximum allowed in the C specification
if oct.length == 1 then
b.add('0')
b.add('0')
else if oct.length == 2 then
b.add('0')
end
b.append(oct)
else
b.add(c)
end
end
return b.to_s
end
# Escape additionnal characters
# The result might no be legal in C but be used in other languages
#
# ~~~
# assert "ab|\{\}".escape_more_to_c("|\{\}") == "ab\\|\\\{\\\}"
# assert "allo???!".escape_more_to_c("") == "allo??\\?!"
# ~~~
fun escape_more_to_c(chars: String): String
do
var b = new Buffer
for c in escape_to_c.chars do
if chars.chars.has(c) then
b.add('\\')
end
b.add(c)
end
return b.to_s
end
# Escape to C plus braces
#
# ~~~
# assert "\n\"'\\\{\}".escape_to_nit == "\\n\\\"\\'\\\\\\\{\\\}"
# ~~~
fun escape_to_nit: String do return escape_more_to_c("\{\}")
# Escape to POSIX Shell (sh).
#
# Abort if the text contains a null byte.
#
# ~~~
# assert "\n\"'\\\{\}0".escape_to_sh == "'\n\"'\\''\\\{\}0'"
# ~~~
fun escape_to_sh: String do
var b = new Buffer
b.chars.add '\''
for i in [0..length[ do
var c = chars[i]
if c == '\'' then
b.append("'\\''")
else
assert without_null_byte: c != '\0'
b.add(c)
end
end
b.chars.add '\''
return b.to_s
end
# Escape to include in a Makefile
#
# Unfortunately, some characters are not escapable in Makefile.
# These characters are `;`, `|`, `\`, and the non-printable ones.
# They will be rendered as `"?{hex}"`.
fun escape_to_mk: String do
var b = new Buffer
for i in [0..length[ do
var c = chars[i]
if c == '$' then
b.append("$$")
else if c == ':' or c == ' ' or c == '#' then
b.add('\\')
b.add(c)
else if c.code_point < 32 or c == ';' or c == '|' or c == '\\' then
b.append("?{c.code_point.to_base(16)}")
else
b.add(c)
end
end
return b.to_s
end
# Return a string where Nit escape sequences are transformed.
#
# ~~~
# var s = "\\n"
# assert s.length == 2
# var u = s.unescape_nit
# assert u.length == 1
# assert u.chars[0].code_point == 10 # (the ASCII value of the "new line" character)
# ~~~
fun unescape_nit: String
do
var res = new Buffer.with_cap(self.length)
var was_slash = false
for i in [0..length[ do
var c = chars[i]
if not was_slash then
if c == '\\' then
was_slash = true
else
res.add(c)
end
continue
end
was_slash = false
if c == 'n' then
res.add('\n')
else if c == 'r' then
res.add('\r')
else if c == 't' then
res.add('\t')
else if c == '0' then
res.add('\0')
else
res.add(c)
end
end
return res.to_s
end
# Returns `self` with all characters escaped with their UTF-16 representation
#
# ~~~
# assert "Aèあ𐏓".escape_to_utf16 == "\\u0041\\u00e8\\u3042\\ud800\\udfd3"
# ~~~
fun escape_to_utf16: String do
var buf = new Buffer
for i in chars do buf.append i.escape_to_utf16
return buf.to_s
end
# Returns the Unicode char escaped by `self`
#
# ~~~
# assert "\\u0041".from_utf16_escape == 'A'
# assert "\\ud800\\udfd3".from_utf16_escape == '𐏓'
# assert "\\u00e8".from_utf16_escape == 'è'
# assert "\\u3042".from_utf16_escape == 'あ'
# ~~~
fun from_utf16_escape(pos, ln: nullable Int): Char do
if pos == null then pos = 0
if ln == null then ln = length - pos
if ln < 6 then return 0xFFFD.code_point
var cp = from_utf16_digit(pos + 2).to_u32
if cp < 0xD800u32 then return cp.code_point
if cp > 0xDFFFu32 then return cp.code_point
if cp > 0xDBFFu32 then return 0xFFFD.code_point
if ln == 6 then return 0xFFFD.code_point
if ln < 12 then return 0xFFFD.code_point
cp <<= 16
cp += from_utf16_digit(pos + 8).to_u32
var cplo = cp & 0xFFFFu32
if cplo < 0xDC00u32 then return 0xFFFD.code_point
if cplo > 0xDFFFu32 then return 0xFFFD.code_point
return cp.from_utf16_surr.code_point
end
# Returns a UTF-16 escape value
#
# ~~~
# var s = "\\ud800\\udfd3"
# assert s.from_utf16_digit(2) == 0xD800
# assert s.from_utf16_digit(8) == 0xDFD3
# ~~~
fun from_utf16_digit(pos: nullable Int): Int do
if pos == null then pos = 0
return to_hex(pos, 4)
end
# Encode `self` to percent (or URL) encoding
#
# ~~~
# assert "aBc09-._~".to_percent_encoding == "aBc09-._~"
# assert "%()< >".to_percent_encoding == "%25%28%29%3c%20%3e"
# assert ".com/post?e=asdf&f=123".to_percent_encoding == ".com%2fpost%3fe%3dasdf%26f%3d123"
# assert "éあいう".to_percent_encoding == "%c3%a9%e3%81%82%e3%81%84%e3%81%86"
# ~~~
fun to_percent_encoding: String
do
var buf = new Buffer
for i in [0..length[ do
var c = chars[i]
if (c >= '0' and c <= '9') or
(c >= 'a' and c <= 'z') or
(c >= 'A' and c <= 'Z') or
c == '-' or c == '.' or
c == '_' or c == '~'
then
buf.add c
else
var bytes = c.to_s.bytes
for b in bytes do buf.append "%{b.to_i.to_hex}"
end
end
return buf.to_s
end
# Decode `self` from percent (or URL) encoding to a clear string
#
# Invalid '%' are not decoded.
#
# ~~~
# assert "aBc09-._~".from_percent_encoding == "aBc09-._~"
# assert "%25%28%29%3c%20%3e".from_percent_encoding == "%()< >"
# assert ".com%2fpost%3fe%3dasdf%26f%3d123".from_percent_encoding == ".com/post?e=asdf&f=123"
# assert "%25%28%29%3C%20%3E".from_percent_encoding == "%()< >"
# assert "incomplete %".from_percent_encoding == "incomplete %"
# assert "invalid % usage".from_percent_encoding == "invalid % usage"
# assert "%c3%a9%e3%81%82%e3%81%84%e3%81%86".from_percent_encoding == "éあいう"
# assert "%1 %A %C3%A9A9".from_percent_encoding == "%1 %A éA9"
# ~~~
fun from_percent_encoding: String
do
var len = byte_length
var has_percent = false
for c in chars do
if c == '%' then
len -= 2
has_percent = true
end
end
# If no transformation is needed, return self as a string
if not has_percent then return to_s
var buf = new CString(len)
var i = 0
var l = 0
while i < length do
var c = chars[i]
if c == '%' then
if i + 2 >= length then
# What follows % has been cut off
buf[l] = u'%'
else
i += 1
var hex_s = substring(i, 2)
if hex_s.is_hex then
var hex_i = hex_s.to_hex
buf[l] = hex_i
i += 1
else
# What follows a % is not Hex
buf[l] = u'%'
i -= 1
end
end
else buf[l] = c.code_point
i += 1
l += 1
end
return buf.to_s_unsafe(l, copy=false)
end
# Escape the characters `<`, `>`, `&`, `"`, `'` and `/` as HTML/XML entity references.
#
# ~~~
# assert "a&b-<>\"x\"/'".html_escape == "a&b-<>"x"/'"
# ~~~
#
# SEE: <https://www.owasp.org/index.php/XSS_%28Cross_Site_Scripting%29_Prevention_Cheat_Sheet#RULE_.231_-_HTML_Escape_Before_Inserting_Untrusted_Data_into_HTML_Element_Content>
fun html_escape: String
do
var buf: nullable Buffer = null
for i in [0..length[ do
var c = chars[i]
var sub = null
if c == '&' then
sub = "&"
else if c == '<' then
sub = "<"
else if c == '>' then
sub = ">"
else if c == '"' then
sub = """
else if c == '\'' then
sub = "'"
else if c == '/' then
sub = "/"
else
if buf != null then buf.add c
continue
end
if buf == null then
buf = new Buffer
for j in [0..i[ do buf.add chars[j]
end
buf.append sub
end
if buf == null then return self.to_s
return buf.to_s
end
# Equality of text
# Two pieces of text are equals if thez have the same characters in the same order.
#
# ~~~
# assert "hello" == "hello"
# assert "hello" != "HELLO"
# assert "hello" == "hel"+"lo"
# ~~~
#
# Things that are not Text are not equal.
#
# ~~~
# assert "9" != '9'
# assert "9" != ['9']
# assert "9" != 9
#
# assert "9".chars.first == '9' # equality of Char
# assert "9".chars == ['9'] # equality of Sequence
# assert "9".to_i == 9 # equality of Int
# ~~~
redef fun ==(o)
do
if o == null then return false
if not o isa Text then return false
if self.is_same_instance(o) then return true
if self.length != o.length then return false
return self.chars == o.chars
end
# Lexicographical comparaison
#
# ~~~
# assert "abc" < "xy"
# assert "ABC" < "abc"
# ~~~
redef fun <(other)
do
var self_chars = self.chars.iterator
var other_chars = other.chars.iterator
while self_chars.is_ok and other_chars.is_ok do
if self_chars.item < other_chars.item then return true
if self_chars.item > other_chars.item then return false
self_chars.next
other_chars.next
end
if self_chars.is_ok then
return false
else
return true
end
end
# Escape string used in labels for graphviz
#
# ~~~
# assert ">><<".escape_to_dot == "\\>\\>\\<\\<"
# ~~~
fun escape_to_dot: String
do
return escape_more_to_c("|\{\}<>")
end
private var hash_cache: nullable Int = null
redef fun hash
do
if hash_cache == null then
# djb2 hash algorithm
var h = 5381
for i in [0..length[ do
var char = chars[i]
h = (h << 5) + h + char.code_point
end
hash_cache = h
end
return hash_cache.as(not null)
end
# Format `self` by replacing each `%n` with the `n`th item of `args`
#
# The character `%` followed by something other than a number are left as is.
# To represent a `%` followed by a number, double the `%`, as in `%%7`.
#
# ~~~
# assert "This %0 is a %1.".format("String", "formatted String") == "This String is a formatted String."
# assert "Do not escape % nor %%1".format("unused") == "Do not escape % nor %1"
# ~~~
fun format(args: Object...): String do
var s = new Array[Text]
var curr_st = 0
var i = 0
while i < length do
if self[i] == '%' then
var fmt_st = i
i += 1
var ciph_st = i
while i < length and self[i].is_numeric do
i += 1
end
var ciph_len = i - ciph_st
if ciph_len == 0 then
# What follows '%' is not a number.
s.push substring(curr_st, i - curr_st)
if i < length and self[i] == '%' then
# Skip the next `%`
i += 1
end
curr_st = i
continue
end
var arg_index = substring(ciph_st, ciph_len).to_i
if arg_index >= args.length then continue
s.push substring(curr_st, fmt_st - curr_st)
s.push args[arg_index].to_s
curr_st = i
i -= 1
end
i += 1
end
s.push substring(curr_st, length - curr_st)
return s.plain_to_s
end
# Return the Levenshtein distance between two strings
#
# ~~~
# assert "abcd".levenshtein_distance("abcd") == 0
# assert "".levenshtein_distance("abcd") == 4
# assert "abcd".levenshtein_distance("") == 4
# assert "abcd".levenshtein_distance("xyz") == 4
# assert "abcd".levenshtein_distance("xbdy") == 3
# ~~~
fun levenshtein_distance(other: String): Int
do
var slen = self.length
var olen = other.length
# fast cases
if slen == 0 then return olen
if olen == 0 then return slen
if self == other then return 0
# previous row of distances
var v0 = new Array[Int].with_capacity(olen+1)
# current row of distances
var v1 = new Array[Int].with_capacity(olen+1)
for j in [0..olen] do
# prefix insert cost
v0[j] = j
end
for i in [0..slen[ do
# prefix delete cost
v1[0] = i + 1
for j in [0..olen[ do
# delete cost
var cost1 = v1[j] + 1
# insert cost
var cost2 = v0[j + 1] + 1
# same char cost (+0)
var cost3 = v0[j]
# change cost
if self[i] != other[j] then cost3 += 1
# keep the min
v1[j+1] = cost1.min(cost2).min(cost3)
end
# Switch columns:
# * v1 become v0 in the next iteration
# * old v0 is reused as the new v1
var tmp = v1
v1 = v0
v0 = tmp
end
return v0[olen]
end
# Copies `n` bytes from `self` at `src_offset` into `dest` starting at `dest_offset`
#
# Basically a high-level synonym of CString::copy_to
#
# REQUIRE: `n` must be large enough to contain `len` bytes
#
# ~~~
# var ns = new CString(8)
# "Text is String".copy_to_native(ns, 8, 2, 0)
# assert ns.to_s_with_length(8) == "xt is St"
# ~~~
fun copy_to_native(dest: CString, n, src_offset, dest_offset: Int) do
var mypos = src_offset
var itspos = dest_offset
while n > 0 do
dest[itspos] = self.bytes[mypos]
itspos += 1
mypos += 1
n -= 1
end
end
# Packs the content of a string in packs of `ln` chars.
# This variant ensures that only the last element might be smaller than `ln`
#
# ~~~
# var s = "abcdefghijklmnopqrstuvwxyz"
# assert s.pack_l(4) == ["abcd","efgh","ijkl","mnop","qrst","uvwx","yz"]
# ~~~
fun pack_l(ln: Int): Array[Text] do
var st = 0
var retarr = new Array[Text].with_capacity(length / ln + length % ln)
while st < length do
retarr.add(substring(st, ln))
st += ln
end
return retarr
end
# Packs the content of a string in packs of `ln` chars.
# This variant ensures that only the first element might be smaller than `ln`
#
# ~~~
# var s = "abcdefghijklmnopqrstuvwxyz"
# assert s.pack_r(4) == ["ab","cdef","ghij","klmn","opqr","stuv","wxyz"]
# ~~~
fun pack_r(ln: Int): Array[Text] do
var st = length
var retarr = new Array[Text].with_capacity(length / ln + length % ln)
while st >= 0 do
retarr.add(substring(st - ln, ln))
st -= ln
end
return retarr.reversed
end
# Concatenates self `i` times
#
# ~~~
# assert "abc" * 4 == "abcabcabcabc"
# assert "abc" * 1 == "abc"
# assert "abc" * 0 == ""
# var b = new Buffer
# b.append("天地")
# b = b * 4
# assert b == "天地天地天地天地"
# ~~~
fun *(i: Int): SELFTYPE is abstract
# Insert `s` at `pos`.
#
# ~~~
# assert "helloworld".insert_at(" ", 5) == "hello world"
# var b = new Buffer
# b.append("Hello世界")
# b = b.insert_at(" beautiful ", 5)
# assert b == "Hello beautiful 世界"
# ~~~
fun insert_at(s: String, pos: Int): SELFTYPE is abstract
# Returns a reversed version of self
#
# ~~~
# assert "hello".reversed == "olleh"
# assert "bob".reversed == "bob"
# assert "".reversed == ""
# ~~~
fun reversed: SELFTYPE is abstract
# A upper case version of `self`
#
# ~~~
# assert "Hello World!".to_upper == "HELLO WORLD!"
# ~~~
fun to_upper: SELFTYPE is abstract
# A lower case version of `self`
#
# ~~~
# assert "Hello World!".to_lower == "hello world!"
# ~~~
fun to_lower : SELFTYPE is abstract
# Takes a camel case `self` and converts it to snake case
#
# ~~~
# assert "randomMethodId".to_snake_case == "random_method_id"
# ~~~
#
# The rules are the following:
#
# An uppercase is always converted to a lowercase
#
# ~~~
# assert "HELLO_WORLD".to_snake_case == "hello_world"
# ~~~
#
# An uppercase that follows a lowercase is prefixed with an underscore
#
# ~~~
# assert "HelloTheWORLD".to_snake_case == "hello_the_world"
# ~~~
#
# An uppercase that follows an uppercase and is followed by a lowercase, is prefixed with an underscore
#
# ~~~
# assert "HelloTHEWorld".to_snake_case == "hello_the_world"
# ~~~
#
# All other characters are kept as is; `self` does not need to be a proper CamelCased string.
#
# ~~~
# assert "=-_H3ll0Th3W0rld_-=".to_snake_case == "=-_h3ll0th3w0rld_-="
# ~~~
fun to_snake_case: SELFTYPE is abstract
# Takes a snake case `self` and converts it to camel case
#
# ~~~
# assert "random_method_id".to_camel_case == "randomMethodId"
# ~~~
#
# If the identifier is prefixed by an underscore, the underscore is ignored
#
# ~~~
# assert "_private_field".to_camel_case == "_privateField"
# ~~~
#
# If `self` is upper, it is returned unchanged
#
# ~~~
# assert "RANDOM_ID".to_camel_case == "RANDOM_ID"
# ~~~
#
# If there are several consecutive underscores, they are considered as a single one
#
# ~~~
# assert "random__method_id".to_camel_case == "randomMethodId"
# ~~~
fun to_camel_case: SELFTYPE is abstract
# Returns a capitalized `self`
#
# Letters that follow a letter are lowercased
# Letters that follow a non-letter are upcased.
#
# If `keep_upper = true`, already uppercase letters are not lowercased.
#
# SEE : `Char::is_letter` for the definition of letter.
#
# ~~~
# assert "jAVASCRIPT".capitalized == "Javascript"
# assert "i am root".capitalized == "I Am Root"
# assert "ab_c -ab0c ab\nc".capitalized == "Ab_C -Ab0C Ab\nC"
# assert "preserve my ACRONYMS".capitalized(keep_upper=true) == "Preserve My ACRONYMS"
# ~~~
fun capitalized(keep_upper: nullable Bool): SELFTYPE do
if length == 0 then return self
var buf = new Buffer.with_cap(length)
buf.capitalize(keep_upper=keep_upper, src=self)
return buf.to_s
end
end
lib/core/text/abstract_text.nit:25,1--1398,3
redef class Text
# Returns a mutable copy of `self`'s bytes
#
# ~~~nit
# assert "String".to_bytes isa Bytes
# assert "String".to_bytes == [83, 116, 114, 105, 110, 103]
# ~~~
fun to_bytes: Bytes do
var b = new Bytes.with_capacity(byte_length)
append_to_bytes b
return b
end
# Is `self` a valid hexdigest ?
#
# assert "0B1d3F".is_valid_hexdigest
# assert not "5G".is_valid_hexdigest
fun is_valid_hexdigest: Bool do
for i in bytes do if not i.is_valid_hexdigit then return false
return true
end
# Appends `self.bytes` to `b`
fun append_to_bytes(b: Bytes) do
for s in substrings do
var from = if s isa FlatString then s.first_byte else 0
b.append_ns_from(s.items, s.byte_length, from)
end
end
# Returns a new `Bytes` instance with the digest as content
#
# assert "0B1F4D".hexdigest_to_bytes == [0x0B, 0x1F, 0x4D]
# assert "0B1F4D".hexdigest_to_bytes.hexdigest == "0B1F4D"
#
# Characters that are not hexadecimal digits are ignored.
#
# assert "z0B1 F4\nD".hexdigest_to_bytes.hexdigest == "0B1F4D"
# assert "\\x0b1 \\xf4d".hexdigest_to_bytes.hexdigest == "0B1F4D"
#
# When the number of hexadecimal digit is not even, then a leading 0 is
# implicitly considered to fill the left byte (the most significant one).
#
# assert "1".hexdigest_to_bytes.hexdigest == "01"
# assert "FFF".hexdigest_to_bytes.hexdigest == "0FFF"
#
# `Bytes::hexdigest` is a loosely reverse method since its
# results contain only pairs of uppercase hexadecimal digits.
#
# assert "ABCD".hexdigest_to_bytes.hexdigest == "ABCD"
# assert "a b c".hexdigest_to_bytes.hexdigest == "0ABC"
fun hexdigest_to_bytes: Bytes do
var b = bytes
var max = byte_length
var dlength = 0 # Number of hex digits
var pos = 0
while pos < max do
var c = b[pos]
if c.is_valid_hexdigit then dlength += 1
pos += 1
end
# Allocate the result buffer
var ret = new Bytes.with_capacity((dlength+1) / 2)
var i = (dlength+1) % 2 # current hex digit (1=high, 0=low)
var byte = 0 # current accumulated byte value
pos = 0
while pos < max do
var c = b[pos]
if c.is_valid_hexdigit then
byte = byte << 4 | c.hexdigit_to_byteval
i -= 1
if i < 0 then
# Last digit known: store and restart
ret.add byte
i = 1
byte = 0
end
end
pos += 1
end
return ret
end
# Gets the hexdigest of the bytes of `self`
#
# assert "<STRING/&rt;".hexdigest == "266C743B535452494E47262334373B2672743B"
fun hexdigest: String do
var ln = byte_length
var outns = new CString(ln * 2)
var oi = 0
for i in [0 .. ln[ do
bytes[i].add_digest_at(outns, oi)
oi += 2
end
return new FlatString.with_infos(outns, ln * 2, 0)
end
# Return a `Bytes` instance where Nit escape sequences are transformed.
#
# assert "B\\n\\x41\\u0103D3".unescape_to_bytes.hexdigest == "420A41F0908F93"
#
# `Bytes::chexdigest` is a loosely reverse methods since its result is only made
# of `"\x??"` escape sequences.
#
# assert "\\x41\\x42\\x43".unescape_to_bytes.chexdigest == "\\x41\\x42\\x43"
# assert "B\\n\\x41\\u0103D3".unescape_to_bytes.chexdigest == "\\x42\\x0A\\x41\\xF0\\x90\\x8F\\x93"
fun unescape_to_bytes: Bytes do
var res = new Bytes.with_capacity(self.byte_length)
var was_slash = false
var i = 0
while i < length do
var c = self[i]
if not was_slash then
if c == '\\' then
was_slash = true
else
res.add_char(c)
end
i += 1
continue
end
was_slash = false
if c == 'n' then
res.add_char('\n')
else if c == 'r' then
res.add_char('\r')
else if c == 't' then
res.add_char('\t')
else if c == '0' then
res.add_char('\0')
else if c == 'x' or c == 'X' then
var hx = substring(i + 1, 2)
if hx.is_hex then
res.add hx.to_hex
else
res.add_char(c)
end
i += 2
else if c == 'u' or c == 'U' then
var hx = substring(i + 1, 6)
if hx.is_hex then
res.add_char(hx.to_hex.code_point)
else
res.add_char(c)
end
i += 6
else
res.add_char(c)
end
i += 1
end
return res
end
# Return a `Bytes` by reading 0 and 1.
#
# assert "1010101100001101".binarydigest_to_bytes.hexdigest == "AB0D"
#
# Note that characters that are neither 0 or 1 are just ignored.
#
# assert "a1B01 010\n1100あ001101".binarydigest_to_bytes.hexdigest == "AB0D"
# assert "hello".binarydigest_to_bytes.is_empty
#
# When the number of bits is not divisible by 8, then leading 0 are
# implicitly considered to fill the left byte (the most significant one).
#
# assert "1".binarydigest_to_bytes.hexdigest == "01"
# assert "1111111".binarydigest_to_bytes.hexdigest == "7F"
# assert "1000110100".binarydigest_to_bytes.hexdigest == "0234"
#
# `Bytes::binarydigest` is a loosely reverse method since its
# results contain only 1 and 0 by blocks of 8.
#
# assert "1010101100001101".binarydigest_to_bytes.binarydigest == "1010101100001101"
# assert "1".binarydigest_to_bytes.binarydigest == "00000001"
fun binarydigest_to_bytes: Bytes
do
var b = bytes
var max = byte_length
# Count bits
var bitlen = 0
var pos = 0
while pos < max do
var c = b[pos]
pos += 1
if c == u'0' or c == u'1' then bitlen += 1
end
# Allocate (and take care of the padding)
var ret = new Bytes.with_capacity((bitlen+7) / 8)
var i = (bitlen+7) % 8 # current bit (7th=128, 0th=1)
var byte = 0 # current accumulated byte value
pos = 0
while pos < max do
var c = b[pos]
pos += 1
if c == u'0' then
byte = byte << 1
else if c == u'1' then
byte = byte << 1 | 1
else
continue
end
i -= 1
if i < 0 then
# Last bit known: store and restart
ret.add byte
i = 7
byte = 0
end
end
return ret
end
end
lib/core/bytes.nit:792,1--1013,3
redef class Text
super Pattern
redef fun search_index_in(s, from)
do
assert from >= 0
var stop = s.length - length + 1
while from < stop do
var i = length - 1
while i >= 0 and self[i] == s[i + from] do i -= 1
# Test if we found
if i < 0 then return from
# Not found so try next one
from += 1
end
return -1
end
redef fun search_in(s, from)
do
var pos = search_index_in(s, from)
if pos < 0 then
return null
else
return new Match(s.to_s, pos, length)
end
end
# Search the first occurence of `pattern`.
# Return null if not found.
#
# assert "I say hello to the world!".search("hello").from == 6
# assert "I say goodbye to the world!".search("hello") == null
fun search(pattern: Pattern): nullable Match do return pattern.search_in(self, 0)
# Search the first occurence of `pattern` after `from`.
# The search starts at `from`.
# Return null if not found.
#
# assert "I say hello to the world!".search_from("hello",4).from == 6
# assert "I say hello to the world!".search_from("hello",7) == null
fun search_from(pattern: Pattern, from: Int): nullable Match do return pattern.search_in(self, from)
# Search the last occurence of the text `t`.
#
# assert "bob".search_last("b").from == 2
# assert "bob".search_last("bo").from == 0
# assert "bob".search_last("ob").from == 1
# assert "bobob".search_last("ob").from == 3
# assert "bobbob".search_last("bb").from == 2
# assert "bobbob".search_last("bob").from == 3
# assert "bob".search_last("z") == null
# assert "".search_last("b") == null
fun search_last(t: Text): nullable Match do
return search_last_up_to(t, length)
end
# Search the last occurence of the text `t` before `up_to`.
#
# assert "bobbob".search_last_up_to("b", 3).from == 2
# assert "bobbob".search_last_up_to("b", 6).from == 5
# assert "bobbob".search_last_up_to("b", 0) == null
fun search_last_up_to(t: Text, up_to: Int): nullable Match do
var i = up_to - t.length
while i >= 0 do
if substring(i, t.length) == t then
return new Match(self.to_s, i, t.length)
end
i -= 1
end
return null
end
# Extract a given prefix, if any.
#
# ~~~
# var p = "hello world".prefix("hello")
# assert p != null
# assert p.text_after == " world"
# ~~~
fun prefix(t: Text): nullable Match do
var len = t.length
if substring(0, len) == t then
return new Match(self.to_s, 0, len)
end
return null
end
# Extract a given suffix, if any.
#
# ~~~
# var p = "hello world".suffix("world")
# assert p != null
# assert p.text_before == "hello "
# ~~~
fun suffix(t: Text): nullable Match do
var len = t.length
var from = length - len
if substring(from, len) == t then
return new Match(self.to_s, from, len)
end
return null
end
# Search all occurrences of `pattern` into self.
#
# var a = new Array[Int]
# for i in "hello world".search_all('o') do
# a.add(i.from)
# end
# assert a == [4, 7]
fun search_all(pattern: Pattern): Array[Match] do return pattern.search_all_in(self)
# Split `self` using `pattern` as separator.
#
# assert "hello world".split('o') == ["hell", " w", "rld"]
fun split(pattern: Pattern): Array[String]
do
var matches = pattern.split_in(self)
var res = new Array[String].with_capacity(matches.length)
for m in matches do res.add(m.to_s)
return res
end
# @deprecated alias for `split`
fun split_with(pattern: Pattern): Array[String] do return self.split(pattern)
# Split `self` on the first occurence of `pattern`
#
# assert "hello".split_once_on('l') == ["he", "lo"]
# assert "a, b, c, d, e".split_once_on(", ") == ["a", "b, c, d, e"]
fun split_once_on(pattern: Pattern): Array[SELFTYPE]
do
var m = pattern.search_in(self, 0)
var res = new Array[SELFTYPE]
if m == null then
res.add self
else
res.add substring(0, m.from)
res.add substring_from(m.after)
end
return res
end
# Replace all occurrences of `pattern` with `string`
#
# assert "hlelo".replace("le", "el") == "hello"
# assert "hello".replace('l', "") == "heo"
#
# var t: Text = "hello"
# assert t.replace("hello", new FlatBuffer) == ""
fun replace(pattern: Pattern, string: Text): String
do
return self.split_with(pattern).join(string)
end
# Replace the first occurrence of `pattern` with `string`
#
# assert "hlelo".replace_first("le", "el") == "hello"
# assert "hello".replace_first('l', "") == "helo"
fun replace_first(pattern: Pattern, string: Text): String
do
return self.split_once_on(pattern).join(string)
end
# Does `self` contains at least one instance of `pattern`?
#
# assert "hello".has('l')
# assert "hello".has("ll")
# assert not "hello".has("lll")
fun has(pattern: Pattern): Bool do return pattern.is_in(self)
# Returns a copy of `self` minus all occurences of `pattern`
#
# assert "__init__".remove_all('_') == "init"
# assert "abcd".remove_all("bc") == "ad"
# assert "abcd".remove_all("[ad]".to_re) == "bc"
fun remove_all(pattern: Pattern): String do return split(pattern).join
end
lib/core/text/string_search.nit:328,1--507,3
redef class Text
# Removes the numeric head of `self` if present
#
# intrude import core::fixed_ints_text
# assert "0xFFEF".strip_numhead == "FFEF"
# assert "0o7364".strip_numhead == "7364"
# assert "0b01001".strip_numhead == "01001"
# assert "98".strip_numhead == "98"
private fun strip_numhead: Text do
if get_numhead != "" then return substring_from(2)
return self
end
# Gets the numeric head of `self` if present
# Returns "" otherwise
#
# intrude import core::fixed_ints_text
# assert "0xFEFF".get_numhead == "0x"
# assert "0b01001".get_numhead == "0b"
# assert "0o872".get_numhead == "0o"
# assert "98".get_numhead == ""
private fun get_numhead: Text do
if self.length < 2 then return ""
var c = self[0]
if c != '0' then return ""
c = self[1]
if c == 'x' or c == 'b' or c == 'o' or
c == 'X' or c == 'B' or c == 'O' then return substring(0, 2)
return ""
end
# Removes the numeric extension if present
#
# intrude import core::fixed_ints_text
# assert "0xFEFFu8".strip_numext == "0xFEFF"
# assert "0b01001u8".strip_numext == "0b01001"
# assert "0o872u8".strip_numext == "0o872"
# assert "98".strip_numext == "98"
private fun strip_numext: Text do
var ext = get_numext
if ext != "" then return substring(0, length - ext.length)
return self
end
# Gets the numeric extension (i/u 8/16/32) in `self` is present
# Returns "" otherwise
#
# intrude import core::fixed_ints_text
# assert "0xFEFFu8".get_numext == "u8"
# assert "0b01001u8".get_numext == "u8"
# assert "0o872u8".get_numext == "u8"
# assert "98".get_numext == ""
private fun get_numext: Text do
var len = self.length
var max = if self.length < 3 then self.length else 3
for i in [1 .. max] do
var c = self[len - i]
if c == 'i' or c == 'u' then return substring_from(len - i)
end
return ""
end
# Is `self` a well-formed Integer (i.e. parsable via `to_i`)
#
# assert "123".is_int
# assert "0b1011".is_int
# assert "-34".is_int
# assert "+45".is_int
# assert not "0x_".is_int
# assert not "0xGE".is_int
# assert not "".is_int
# assert not "Not an Int".is_int
# assert not "-".is_int
fun is_int: Bool do
if byte_length == 0 then return false
var s = remove_all('_')
var pos = 0
var len = s.length
while pos < len and (s[pos] == '-' or s[pos] == '+') do
pos += 1
end
s = s.substring_from(pos)
var rets = s.strip_numhead
if rets == "" then return false
var hd = get_numhead
if hd == "0x" or hd == "0X" then return rets.is_hex
if hd == "0b" or hd == "0B" then return rets.is_bin
if hd == "0o" or hd == "0O" then return rets.is_oct
return rets.is_dec
end
redef fun to_i
do
assert self.is_int
var s = remove_all('_')
var val = 0
var neg = false
var pos = 0
loop
if s[pos] == '-' then
neg = not neg
pos += 1
else if s[pos] == '+' then
pos += 1
else
break
end
end
s = s.substring_from(pos)
if s.length >= 2 then
var s1 = s[1]
if s1 == 'x' or s1 == 'X' then
val = s.substring_from(2).to_hex
else if s1 == 'o' or s1 == 'O' then
val = s.substring_from(2).to_oct
else if s1 == 'b' or s1 == 'B' then
val = s.substring_from(2).to_bin
else if s1.is_numeric then
val = s.to_dec
end
else
val = s.to_dec
end
return if neg then -val else val
end
# Is `self` a valid integer ?
#
# assert "0xFE46u8".is_num
# assert "0b0100".is_num
# assert "0o645".is_num
# assert "897u8".is_num
fun is_num: Bool do
var prefix = get_numhead
var s = strip_numhead.strip_numext.remove_all('_')
if prefix != "" then
var c = prefix[1]
if c == 'x' or c == 'X' then return s.is_hex
if c == 'o' or c == 'O' then return s.is_oct
if c == 'b' or c == 'B' then return s.is_bin
end
return s.is_dec
end
# If `self` is a properly formatted integer, returns the corresponding value
# Returns `null` otherwise
#
# assert "0xFEu8".to_num == 254u8
# assert "0b10_10".to_num != 10u8
fun to_num: nullable Numeric do
if not is_num then return null
var s = remove_all('_')
var ext = s.get_numext
var trunk = s.strip_numext
if trunk.strip_numhead == "" then return null
var trval = trunk.to_i
if ext == "u8" then
return trval.to_b
else if ext == "i8" then
return trval.to_i8
else if ext == "i16" then
return trval.to_i16
else if ext == "u16" then
return trval.to_u16
else if ext == "i32" then
return trval.to_i32
else if ext == "u32" then
return trval.to_u32
else if ext == "" then
return trval
else
return null
end
end
end
lib/core/text/fixed_ints_text.nit:144,1--319,3
redef class Text
# Get the numeric version of `self`
#
# require: `is_numeric`
#
# ~~~~
# assert "0".to_n == 0
# assert "0.0".to_n == 0.0
# assert ".12345".to_n == 0.12345
# assert "12345".to_n == 12345
# assert "".to_n == 0
# ~~~~
fun to_n: Numeric
do
if is_empty then return 0
if chars.has('.') then return to_f
return to_i
end
end
lib/core/numeric.nit:23,1--41,3
redef class Text
# Access file system related services on the path at `self`
fun to_path: Path do return new Path(to_s)
private fun write_native_to(s: FileWriter)
do
for i in substrings do s.write_native(i.to_cstring, 0, i.byte_length)
end
# return true if a file with this names exists
fun file_exists: Bool do return to_cstring.file_exists
# The status of a file. see POSIX stat(2).
fun file_stat: nullable FileStat
do
var stat = to_cstring.file_stat
if stat.address_is_null then return null
return new FileStat(stat)
end
# The status of a file or of a symlink. see POSIX lstat(2).
fun file_lstat: nullable FileStat
do
var stat = to_cstring.file_lstat
if stat.address_is_null then return null
return new FileStat(stat)
end
# Remove a file, return true if success
fun file_delete: Bool do return to_cstring.file_delete
# Copy content of file at `self` to `dest`
fun file_copy_to(dest: String) do to_path.copy(dest.to_path)
# Remove the trailing `extension`.
#
# `extension` usually starts with a dot but could be anything.
#
# assert "file.txt".strip_extension(".txt") == "file"
# assert "file.txt".strip_extension("le.txt") == "fi"
# assert "file.txt".strip_extension("xt") == "file.t"
#
# If `extension == null`, the rightmost extension is stripped, including the last dot.
#
# assert "file.txt".strip_extension == "file"
#
# If `extension` is not present, `self` is returned unmodified.
#
# assert "file.txt".strip_extension(".tar.gz") == "file.txt"
fun strip_extension(extension: nullable String): String
do
if extension == null then
extension = file_extension
if extension == null then
return self.to_s
else extension = ".{extension}"
end
if has_suffix(extension) then
return substring(0, length - extension.length).to_s
end
return self.to_s
end
# Extract the basename of a path and strip the `extension`
#
# The extension is stripped only if `extension != null`.
#
# assert "/path/to/a_file.ext".basename(".ext") == "a_file"
# assert "path/to/a_file.ext".basename(".ext") == "a_file"
# assert "path/to/a_file.ext".basename == "a_file.ext"
# assert "path/to".basename(".ext") == "to"
# assert "path/to/".basename(".ext") == "to"
# assert "path/to".basename == "to"
# assert "path".basename == "path"
# assert "/path".basename == "path"
# assert "/".basename == "/"
# assert "".basename == ""
#
# On Windows, '\' are replaced by '/':
#
# ~~~nitish
# assert "C:\\path\\to\\a_file.ext".basename(".ext") == "a_file"
# assert "C:\\".basename == "C:"
# ~~~
fun basename(extension: nullable String): String
do
var n = self
if is_windows then n = n.replace("\\", "/")
var l = length - 1 # Index of the last char
while l > 0 and self.chars[l] == '/' do l -= 1 # remove all trailing `/`
if l == 0 then return "/"
var pos = chars.last_index_of_from('/', l)
if pos >= 0 then
n = substring(pos+1, l-pos)
end
if extension != null then
return n.strip_extension(extension)
else return n.to_s
end
# Extract the dirname of a path
#
# assert "/path/to/a_file.ext".dirname == "/path/to"
# assert "path/to/a_file.ext".dirname == "path/to"
# assert "path/to".dirname == "path"
# assert "path/to/".dirname == "path"
# assert "path".dirname == "."
# assert "/path".dirname == "/"
# assert "/".dirname == "/"
# assert "".dirname == "."
#
# On Windows, '\' are replaced by '/':
#
# ~~~nitish
# assert "C:\\path\\to\\a_file.ext".dirname == "C:/path/to"
# assert "C:\\file".dirname == "C:"
# ~~~
fun dirname: String
do
var s = self
if is_windows then s = s.replace("\\", "/")
var l = length - 1 # Index of the last char
while l > 0 and s.chars[l] == '/' do l -= 1 # remove all trailing `/`
var pos = s.chars.last_index_of_from('/', l)
if pos > 0 then
return s.substring(0, pos).to_s
else if pos == 0 then
return "/"
else
return "."
end
end
# Return the canonicalized absolute pathname (see POSIX function `realpath`)
#
# Require: `file_exists`
fun realpath: String do
var cs = to_cstring.file_realpath
assert file_exists
var res = cs.to_s
cs.free
return res
end
# Simplify a file path by remove useless `.`, removing `//`, and resolving `..`
#
# * `..` are not resolved if they start the path
# * starting `.` is simplified unless the path is empty
# * starting `/` is not removed
# * trailing `/` is removed
#
# Note that the method only work on the string:
#
# * no I/O access is performed
# * the validity of the path is not checked
#
# ~~~
# assert "some/./complex/../../path/from/../to/a////file//".simplify_path == "path/to/a/file"
# assert "../dir/file".simplify_path == "../dir/file"
# assert "dir/../../".simplify_path == ".."
# assert "dir/..".simplify_path == "."
# assert "//absolute//path/".simplify_path == "/absolute/path"
# assert "//absolute//../".simplify_path == "/"
# assert "/".simplify_path == "/"
# assert "../".simplify_path == ".."
# assert "./".simplify_path == "."
# assert "././././././".simplify_path == "."
# assert "./../dir".simplify_path == "../dir"
# assert "./dir".simplify_path == "dir"
# ~~~
#
# On Windows, '\' are replaced by '/':
#
# ~~~nitish
# assert "C:\\some\\.\\complex\\../../path/to/a_file.ext".simplify_path == "C:/path/to/a_file.ext"
# assert "C:\\".simplify_path == "C:"
# ~~~
fun simplify_path: String
do
var s = self
if is_windows then s = s.replace("\\", "/")
var a = s.split_with("/")
var a2 = new Array[String]
for x in a do
if x == "." and not a2.is_empty then continue # skip `././`
if x == "" and not a2.is_empty then continue # skip `//`
if x == ".." and not a2.is_empty and a2.last != ".." then
if a2.last == "." then # do not skip `./../`
a2.pop # reduce `./../` in `../`
else # reduce `dir/../` in `/`
a2.pop
continue
end
else if not a2.is_empty and a2.last == "." then
a2.pop # reduce `./dir` in `dir`
end
a2.push(x)
end
if a2.is_empty then return "."
if a2.length == 1 and a2.first == "" then return "/"
return a2.join("/")
end
# Correctly join two path using the directory separator.
#
# Using a standard "{self}/{path}" does not work in the following cases:
#
# * `self` is empty.
# * `path` starts with `'/'`.
#
# This method ensures that the join is valid.
#
# assert "hello".join_path("world") == "hello/world"
# assert "hel/lo".join_path("wor/ld") == "hel/lo/wor/ld"
# assert "".join_path("world") == "world"
# assert "hello".join_path("/world") == "/world"
# assert "hello/".join_path("world") == "hello/world"
# assert "hello/".join_path("/world") == "/world"
#
# Note: You may want to use `simplify_path` on the result.
#
# Note: This method works only with POSIX paths.
fun join_path(path: Text): String
do
if path.is_empty then return self.to_s
if self.is_empty then return path.to_s
if path.chars[0] == '/' then return path.to_s
if self.last == '/' then return "{self}{path}"
return "{self}/{path}"
end
# Convert the path (`self`) to a program name.
#
# Ensure the path (`self`) will be treated as-is by POSIX shells when it is
# used as a program name. In order to do that, prepend `./` if needed.
#
# assert "foo".to_program_name == "./foo"
# assert "/foo".to_program_name == "/foo"
# assert "".to_program_name == "./" # At least, your shell will detect the error.
fun to_program_name: String do
if self.has_prefix("/") then
return self.to_s
else
return "./{self}"
end
end
# Alias for `join_path`
#
# assert "hello" / "world" == "hello/world"
# assert "hel/lo" / "wor/ld" == "hel/lo/wor/ld"
# assert "" / "world" == "world"
# assert "/hello" / "/world" == "/world"
#
# This operator is quite useful for chaining changes of path.
# The next one being relative to the previous one.
#
# var a = "foo"
# var b = "/bar"
# var c = "baz/foobar"
# assert a/b/c == "/bar/baz/foobar"
fun /(path: Text): String do return join_path(path)
# Returns the relative path needed to go from `self` to `dest`.
#
# assert "/foo/bar".relpath("/foo/baz") == "../baz"
# assert "/foo/bar".relpath("/baz/bar") == "../../baz/bar"
#
# If `self` or `dest` is relative, they are considered relatively to `getcwd`.
#
# In some cases, the result is still independent of the current directory:
#
# assert "foo/bar".relpath("..") == "../../.."
#
# In other cases, parts of the current directory may be exhibited:
#
# var p = "../foo/bar".relpath("baz")
# var c = getcwd.basename
# assert p == "../../{c}/baz"
#
# For path resolution independent of the current directory (eg. for paths in URL),
# or to use an other starting directory than the current directory,
# just force absolute paths:
#
# var start = "/a/b/c/d"
# var p2 = (start/"../foo/bar").relpath(start/"baz")
# assert p2 == "../../d/baz"
#
#
# Neither `self` or `dest` has to be real paths or to exist in directories since
# the resolution is only done with string manipulations and without any access to
# the underlying file system.
#
# If `self` and `dest` are the same directory, the empty string is returned:
#
# assert "foo".relpath("foo") == ""
# assert "foo/../bar".relpath("bar") == ""
#
# The empty string and "." designate both the current directory:
#
# assert "".relpath("foo/bar") == "foo/bar"
# assert ".".relpath("foo/bar") == "foo/bar"
# assert "foo/bar".relpath("") == "../.."
# assert "/" + "/".relpath(".") == getcwd
fun relpath(dest: String): String
do
# TODO windows support
var cwd = getcwd
var from = (cwd/self).simplify_path.split("/")
if from.last.is_empty then from.pop # case for the root directory
var to = (cwd/dest).simplify_path.split("/")
if to.last.is_empty then to.pop # case for the root directory
# Remove common prefixes
while not from.is_empty and not to.is_empty and from.first == to.first do
from.shift
to.shift
end
# Result is going up in `from` with ".." then going down following `to`
var from_len = from.length
if from_len == 0 then return to.join("/")
var up = "../"*(from_len-1) + ".."
if to.is_empty then return up
var res = up + "/" + to.join("/")
return res
end
# Create a directory (and all intermediate directories if needed)
#
# The optional `mode` parameter specifies the permissions of the directory,
# the default value is `0o777`.
#
# Return an error object in case of error.
#
# assert "/etc/".mkdir != null
fun mkdir(mode: nullable Int): nullable Error
do
mode = mode or else 0o777
var s = self
if is_windows then s = s.replace("\\", "/")
var dirs = s.split_with("/")
var path = new FlatBuffer
if dirs.is_empty then return null
if dirs[0].is_empty then
# it was a starting /
path.add('/')
end
var error: nullable Error = null
for i in [0 .. dirs.length - 1[ do
var d = dirs[i]
if d.is_empty then continue
path.append(d)
path.add('/')
if path.file_exists then continue
var res = path.to_cstring.file_mkdir(mode)
if not res and error == null then
error = new IOError("Cannot create directory `{path}`: {sys.errno.strerror}")
end
end
var res = s.to_cstring.file_mkdir(mode)
if not res and error == null then
error = new IOError("Cannot create directory `{path}`: {sys.errno.strerror}")
end
return error
end
# Delete a directory and all of its content, return `true` on success
#
# Does not go through symbolic links and may get stuck in a cycle if there
# is a cycle in the filesystem.
#
# Return an error object in case of error.
#
# assert "/fail/does not/exist".rmdir != null
fun rmdir: nullable Error
do
var p = to_path
p.rmdir
return p.last_error
end
# Change the current working directory
#
# "/etc".chdir
# assert getcwd == "/etc"
# "..".chdir
# assert getcwd == "/"
#
# Return an error object in case of error.
#
# assert "/etc".chdir == null
# assert "/fail/does no/exist".chdir != null
# assert getcwd == "/etc" # unchanger
fun chdir: nullable Error
do
var res = to_cstring.file_chdir
if res then return null
var error = new IOError("Cannot change directory to `{self}`: {sys.errno.strerror}")
return error
end
# Return right-most extension (without the dot)
#
# Only the last extension is returned.
# There is no special case for combined extensions.
#
# assert "file.txt".file_extension == "txt"
# assert "file.tar.gz".file_extension == "gz"
#
# For file without extension, `null` is returned.
# Hoever, for trailing dot, `""` is returned.
#
# assert "file".file_extension == null
# assert "file.".file_extension == ""
#
# The starting dot of hidden files is never considered.
#
# assert ".file.txt".file_extension == "txt"
# assert ".file".file_extension == null
fun file_extension: nullable String
do
var last_slash = chars.last_index_of('.')
if last_slash > 0 then
return substring( last_slash+1, length ).to_s
else
return null
end
end
# Returns entries contained within the directory represented by self.
#
# var files = "/etc".files
# assert files.has("issue")
#
# Returns an empty array in case of error
#
# files = "/etc/issue".files
# assert files.is_empty
#
# TODO find a better way to handle errors and to give them back to the user.
fun files: Array[String]
do
var res = new Array[String]
var d = new NativeDir.opendir(to_cstring)
if d.address_is_null then return res
loop
var de = d.readdir
if de.address_is_null then break
var name = de.to_s
if name == "." or name == ".." then continue
res.add name
end
d.closedir
return res
end
end
lib/core/file.nit:892,1--1355,3
redef class Text
# Encodes the receiver string to base64 using a custom padding character.
#
# If using the default padding character `=`, see `encode_base64`.
fun encode_base64: String do return to_cstring.encode_base64(byte_length).to_s
# Decodes the receiver string to base64 using a custom padding character.
#
# Default padding character `=`
fun decode_base64: Bytes do return to_cstring.decode_base64(byte_length)
# Is `self` a well-formed Base64 entity ?
fun is_base64: Bool do return to_cstring.is_base64(byte_length)
# Is `self` a well-formed Base64 entity ?
#
# Will return an Error otherwise with info on which part is erroneous.
fun check_base64: nullable Error do return to_cstring.check_base64(byte_length)
end
lib/base64/base64.nit:221,1--240,3
redef class Text
# Get a `NSString` from `self`
fun to_nsstring: NSString do return to_cstring.to_nsstring(byte_length)
end
lib/cocoa/foundation.nit:52,1--55,3
# Services to color terminal output
redef class Text
private fun apply_format(f: TermCharFormat): String do
if stdout_isatty or force_console_colors then
return "{f}{self}{normal}"
else return to_s
end
private fun normal: TermCharFormat do return new TermCharFormat
# Make the text appear in dark gray (or black) in a ANSI/VT100 terminal.
#
# SEE: `TermCharFormat`
fun gray: String do return apply_format(normal.black_fg)
# Make the text appear in red in a ANSI/VT100 terminal.
#
# SEE: `TermCharFormat`
fun red: String do return apply_format(normal.red_fg)
# Make the text appear in green in a ANSI/VT100 terminal.
#
# SEE: `TermCharFormat`
fun green: String do return apply_format(normal.green_fg)
# Make the text appear in yellow in a ANSI/VT100 terminal.
#
# SEE: `TermCharFormat`
fun yellow: String do return apply_format(normal.yellow_fg)
# Make the text appear in blue in a ANSI/VT100 terminal.
#
# SEE: `TermCharFormat`
fun blue: String do return apply_format(normal.blue_fg)
# Make the text appear in magenta in a ANSI/VT100 terminal.
#
# SEE: `TermCharFormat`
fun purple: String do return apply_format(normal.magenta_fg)
# Make the text appear in cyan in a ANSI/VT100 terminal.
#
# SEE: `TermCharFormat`
fun cyan: String do return apply_format(normal.cyan_fg)
# Make the text appear in light gray (or white) in a ANSI/VT100 terminal.
#
# SEE: `TermCharFormat`
fun light_gray: String do return apply_format(normal.white_fg)
# Make the text appear in bold in a ANSI/VT100 terminal.
#
# SEE: `TermCharFormat`
fun bold: String do return apply_format(normal.bold)
# Make the text underlined in a ANSI/VT100 terminal.
#
# SEE: `TermCharFormat`
fun underline: String do return apply_format(normal.underline)
end
lib/console/console.nit:286,1--345,3
redef class Text
# Get `self` as a `CppString`
fun to_cpp_string: CppString do return to_cstring.to_cpp_string(length)
end
lib/cpp/cpp.nit:26,1--29,3
redef class Text
# Score `self` according to english's letter frequency.
# This function is useful mainly for cryptography but could happen to be helpful
# elsewhere.
#
# assert "aaaa".english_scoring > "bbbb".english_scoring
fun english_scoring: Float do
var freqs = english_freqs
var score = 0.0
for c in self do
c = c.to_lower
var points = freqs.get_or_null(c)
if points != null then
score += points
end
end
return score
end
end
lib/crapto/english_utils.nit:57,1--80,3
redef class Text
# Performs a Rotation of `x` on each letter of self
#
# Works by replacing every character in `self` by its
# rotated char.
#
# Say we have a rotation of `3` (Caesar rotation, for
# culture) for a string : "aybabtu"
#
# a, rotated by 3 becomes d
# y, rotated by 3 becomes b
# b, rotated by 3 becomes e
# t, rotated by 3 becomes w
# u, rotated by 3 becomes x
#
# We then replace every letter in our original string by
# their rotated representations, therefore yielding : "dbedewx"
#
# assert "All your base are belong to us".rot(13) == "Nyy lbhe onfr ner orybat gb hf"
# assert "This is no moon.".rot(4).rot(22) == "This is no moon."
#
# NOTE : Works on letters only
# NOTE : This cipher is symmetrically decrypted with an `x` of 26-`x`
fun rot(x: Int): Text do
var rot = x % 26
if rot < 0 then rot += 26
var d = new FlatBuffer.with_capacity(length)
for i in chars do
d.add i.rot(rot)
end
return d.to_s
end
# Returns a rail-fence cipher from `self` with `depth` rails
#
# Rail works by drawing a zig-zag pattern on `depth` rails.
#
# Say we have "fuckingbehemoth".railfence(4)
#
# This happens in-memory:
#
# ~~~raw
# f.....g.....o..
# .u...n.b...m.t.
# ..c.i...e.e...h
# ...k.....h.....
# ~~~
#
# Therefore, yielding the ciphertext : "fgounbmtcieehkh"
#
# assert "fuckingbehemoth".railfence(4) == "fgounbmtcieehkh"
fun railfence(depth: Int): Text do
var lines = new Array[FlatBuffer].with_capacity(depth)
var up = false
for i in [0..depth[ do
lines[i] = new FlatBuffer.with_capacity(length)
end
var curr_depth = 0
for i in chars do
for j in [0..depth[ do
if j == curr_depth then
lines[j].add i
else
lines[j].add '.'
end
end
if up then
curr_depth -= 1
else
curr_depth += 1
end
if curr_depth == 0 then
up = false
end
if curr_depth == (depth - 1) then
up = true
end
end
var r = new FlatBuffer.with_capacity(length)
for i in lines do
r.append i.to_s.replace(".", "")
end
return r.to_s
end
# Transforms a rail-fence-encrypted Text to its original
#
# assert "fgounbmtcieehkh".unrail(4) == "fuckingbehemoth"
fun unrail(depth: Int): Text do
var dots = "." * length
var arr = new FlatBuffer.from(dots)
var start = 0
var paces = depth.unrail_paces
for i in [0..depth[ do
var lp = paces[i].first
var rp = paces[i].second
var pos = i
var l = true
while pos < length do
arr[pos] = chars[start]
if l then
pos += lp
l = false
else
pos += rp
l = true
end
start += 1
end
end
return arr.to_s
end
# Vigenere encoder on ASCII letters.
#
# Only the letters in '[A-Za-z]' are encoded while keeping the case.
#
# assert "Hello, World!".vigenere("abc") == "Hfnlp, Yosnd!"
#
# REQUIRE `key` contains only lowercases '[a-z]'
fun vigenere(key: String): String
do
var res = new Buffer
res.enlarge(length)
var i = 0
for c in self do
var k = key[i%key.length]
assert k >= 'a' and k <= 'z'
if c.is_letter then
var d = k.code_point - 'a'.code_point
c = c.rot(d)
i += 1
end
res.add c
end
return res.to_s
end
# Vigenere decoder on ASCII letters.
#
# Only the letters in '[A-Za-z]' are decoded while keeping the case.
#
# assert "Hfnlp, Yosnd!".uvigenere("abc") == "Hello, World!"
#
# REQUIRE `key` contains only lowercases '[a-z]'
fun uvigenere(key: String): String
do
var res = new Buffer
res.enlarge(length)
var i = 0
for c in self do
var k = key[i%key.length]
assert k >= 'a' and k <= 'z'
if c.is_letter then
var d = k.code_point - 'a'.code_point
c = c.rot(-d)
i += 1
end
res.add c
end
return res.to_s
end
end
lib/crypto/basic_ciphers.nit:45,1--207,3
redef class Text
# Escape the content of `self` for inclusion in a CSV document
private fun escape_to_csv(sep_char, delim_char: Char, eol: String): String do
var add_sp = chars_to_escape_csv(sep_char, delim_char, eol)
if add_sp == 0 then return to_s
var bf = new Buffer.with_cap(add_sp + byte_length)
bf.add '"'
for i in [0 .. length[ do
var c = self[i]
if c == delim_char then
bf.add c
end
bf.add c
end
bf.add '"'
return bf.to_s
end
# How many more bytes should be allocated for CSV escaping ?
private fun chars_to_escape_csv(sep_char, delim_char: Char, eol: String): Int do
var more_ln = 0
var ln = length
var need_esc = false
var fst_eol = eol.first
var i = 0
while i < ln do
var c = self[i]
if c == delim_char then more_ln += 1
if c == fst_eol then
need_esc = true
for j in [1 .. eol.length[ do
i += 1
c = self[i]
if c != eol[j] then
i -= j
need_esc = false
break
end
end
end
if c == sep_char then need_esc = true
i += 1
end
var more = more_ln * delim_char.u8char_len
if need_esc then more += 2
return more
end
# Unescape the content of `self` from CSV format to Nit String
private fun unescape_csv(delim_char: Char): String do
var to_un = chars_to_unescape_csv(delim_char)
if to_un == 0 then return to_s
var buf = new Buffer.with_cap(byte_length - to_un)
var pos = 0
var ln = length
while pos < ln do
var c = self[pos]
if c == delim_char then pos += 1
buf.add c
pos += 1
end
return buf.to_s
end
# How many bytes should be removed for CSV unescaping ?
private fun chars_to_unescape_csv(delim_char: Char): Int do
var pos = 0
var to_un = 0
var ln = length
while pos < ln do
var c = self[pos]
if c == delim_char then
pos += 1
to_un += 1
end
pos += 1
end
return to_un
end
end
lib/csv/csv.nit:18,1--97,3
redef class Text
# Run `self` as JavaScript code
fun run_js do run_js_native(self.escape_to_js.to_cstring)
private fun run_js_native(script: CString) `{ emscripten_run_script(script); `}
# Escape the content of `self` to pass to JavaScript code
fun escape_to_js: Text do return replace('\n', "\\n")
# Raise a JavaScript alert
fun alert do "alert('{self.escape_to_js}')".run_js
end
lib/emscripten/emscripten.nit:28,1--39,3
redef class Text
# MD5 digest of `self`
#
# ~~~
# assert "".md5 == "d41d8cd98f00b204e9800998ecf8427e"
# assert "a".md5 == "0cc175b9c0f1b6a831c399e269772661"
# assert "abc".md5 == "900150983cd24fb0d6963f7d28e17f72"
# ~~~
fun md5: String do return to_cstring.native_md5.to_s
end
lib/md5/md5.nit:492,1--501,3
redef class Text
# Writes self as a dot file on the hard drive
private fun internal_to_dot: String is abstract
# Returns the graphviz-formatted content of `self`
fun to_dot: String do
return "digraph g \{\n" + internal_to_dot + "\}\n"
end
end
lib/ropes_debug/ropes_debug.nit:20,1--28,3
redef class Text
# Computes the SHA1 of the receiver
#
# Returns a digest of 20 bytes as a CString,
# note that all the characters are not necessarily ASCII.
# If you want the hex string version of the digest, use
# sha1_hexdigest.
#
# import base64
# assert "The quick brown fox jumps over the lazy dog".sha1 == [0x2F, 0xD4, 0xE1, 0xC6, 0x7A, 0x2D, 0x28, 0xFC, 0xED, 0x84, 0x9E, 0xE1, 0xBB, 0x76, 0xE7, 0x39, 0x1B, 0x93, 0xEB, 0x12]
fun sha1: Bytes do
return new Bytes(to_cstring.sha1_intern(byte_length), 20, 20)
end
# Computes the SHA1 of the receiver.
#
# Returns a 40 char String containing the Hexadecimal
# Digest in its Char form.
#
# assert "The quick brown fox jumps over the lazy dog".sha1_hexdigest == "2FD4E1C67A2D28FCED849EE1BB76E7391B93EB12"
fun sha1_hexdigest: String do return sha1.hexdigest
# Is `self` a SHA-1 hexdigest?
#
#~~~nit
# assert "2FD4E1C67A2D28FCED849EE1BB76E7391B93EB12".is_sha1_digest
# assert not "Not a digest".is_sha1_digest
# assert not "2FD4E1C67A2D28FCED849EE1B76E7391B93EB12".is_sha1_digest
# assert not "2FD4E1C67A2D28FCED849EE1UB76E7391B93EB12".is_sha1_digest
#~~~
fun is_sha1_digest: Bool do return length == 40 and is_hex
end
lib/sha1/sha1.nit:238,1--270,3
redef class Text
# Open the URL `self` with the default browser
fun open_in_browser do print_error "Text::open_in_browser not implemented on this platform."
end
lib/app/ui.nit:333,1--336,3
redef class Text
# Is `self` a well-formed BigInt (i.e. parsable via `to_bi`)
#
# assert "123".is_bi
# assert "-123".is_bi
# assert not "0b1011".is_bi
# assert not "123u8".is_bi
# assert not "Not a BigInt".is_bi
fun is_bi: Bool do
var pre = prefix("-")
if pre != null then
return pre.text_after.is_dec
else
return is_dec
end
end
# Is `self` a well-formed Ratio (i.e. parsable via `to_r`)
#
# assert "123".is_r
# assert "-123".is_r
# assert "1/2".is_r
# assert "-1/2".is_r
# assert not "-1/-2".is_r
# assert not "0b1011".is_r
# assert not "123u8".is_r
# assert not "Not an Ratio".is_r
fun is_r: Bool do
var frac = split_once_on('/')
if frac.length == 2 then
return frac[0].is_bi and frac[1].is_dec
else
return is_bi
end
end
# If `self` contains a BigInt, return the corresponding BigInt
#
# assert("123".to_bi == 123.to_bi)
# assert("-123".to_bi == -123.to_bi)
fun to_bi: BigInt do
assert is_bi
var tmp = new NativeMPZ
tmp.set_str(self.to_cstring, 10i32)
return new BigInt(tmp)
end
# If `self` contains a Ratio, return the corresponding Ratio
#
# assert("123".to_r == 123.to_r)
# assert("-123".to_r == -123.to_r)
# assert("1/2".to_r == 0.5.to_r)
# assert("-1/2".to_r == -0.5.to_r)
fun to_r: Ratio do
assert is_r
var tmp = new NativeMPQ
tmp.set_str self.to_cstring
return new Ratio(tmp)
end
end
lib/gmp/gmp.nit:30,1--90,3
redef class Text
# Get the position of the next non-space character.
private fun skip_spaces(start: Int): Int do
var pos = start
while pos > -1 and pos < length and (self[pos] == ' ' or self[pos] == '\n') do
pos += 1
end
if pos < length then return pos
return -1
end
# Read `self` until `nend` and append it to the `out` buffer.
# Escape markdown special chars.
private fun read_until(out: FlatBuffer, start: Int, nend: Char...): Int do
var pos = start
while pos < length do
var c = self[pos]
if c == '\\' and pos + 1 < length then
pos = escape(out, self[pos + 1], pos)
else
for n in nend do if c == n then break label
out.add c
end
pos += 1
end label
if pos == length then return -1
return pos
end
# Read `self` as raw text until `nend` and append it to the `out` buffer.
# No escape is made.
private fun read_raw_until(out: FlatBuffer, start: Int, nend: Char...): Int do
var pos = start
while pos < length do
var c = self[pos]
var end_reached = false
for n in nend do
if c == n then
end_reached = true
break
end
end
if end_reached then break
out.add c
pos += 1
end
if pos == length then return -1
return pos
end
# Read `self` as XML until `to` and append it to the `out` buffer.
# Escape HTML special chars.
private fun read_xml_until(out: FlatBuffer, from: Int, to: Char...): Int do
var pos = from
var in_str = false
var str_char: nullable Char = null
while pos < length do
var c = self[pos]
if in_str then
if c == '\\' then
out.add c
pos += 1
if pos < length then
out.add c
pos += 1
end
continue
end
if c == str_char then
in_str = false
out.add c
pos += 1
continue
end
end
if c == '"' or c == '\'' then
in_str = true
str_char = c
end
if not in_str then
var end_reached = false
for n in [0..to.length[ do
if c == to[n] then
end_reached = true
break
end
end
if end_reached then break
end
out.add c
pos += 1
end
if pos == length then return -1
return pos
end
# Read `self` as XML and append it to the `out` buffer.
# Safe mode can be activated to limit reading to valid xml.
private fun read_xml(out: FlatBuffer, start: Int, safe_mode: Bool): Int do
var pos = 0
var is_valid = true
var is_close_tag = false
if start + 1 >= length then return -1
if self[start + 1] == '/' then
is_close_tag = true
pos = start + 2
else if self[start + 1] == '!' then
out.append "<!"
return start + 1
else
is_close_tag = false
pos = start + 1
end
if safe_mode then
var tmp = new FlatBuffer
pos = read_xml_until(tmp, pos, ' ', '/', '>')
if pos == -1 then return -1
var tag = tmp.write_to_string.trim.to_lower
if not tag.is_valid_html_tag then
out.append "<"
pos = -1
else if tag.is_html_unsafe then
is_valid = false
out.append "<"
if is_close_tag then out.add '/'
out.append tmp
else
out.append "<"
if is_close_tag then out.add '/'
out.append tmp
end
else
out.add '<'
if is_close_tag then out.add '/'
pos = read_xml_until(out, pos, ' ', '/', '>')
end
if pos == -1 then return -1
pos = read_xml_until(out, pos, '/', '>')
if pos == -1 then return -1
if self[pos] == '/' then
out.append " /"
pos = self.read_xml_until(out, pos + 1, '>')
if pos == -1 then return -1
end
if self[pos] == '>' then
if is_valid then
out.add '>'
else
out.append ">"
end
return pos
end
return -1
end
# Read a markdown link address and append it to the `out` buffer.
private fun read_md_link(out: FlatBuffer, start: Int): Int do
var pos = start
var counter = 1
while pos < length do
var c = self[pos]
if c == '\\' and pos + 1 < length then
pos = escape(out, self[pos + 1], pos)
else
var end_reached = false
if c == '(' then
counter += 1
else if c == ' ' then
if counter == 1 then end_reached = true
else if c == ')' then
counter -= 1
if counter == 0 then end_reached = true
end
if end_reached then break
out.add c
end
pos += 1
end
if pos == length then return -1
return pos
end
# Read a markdown link text and append it to the `out` buffer.
private fun read_md_link_id(out: FlatBuffer, start: Int): Int do
var pos = start
var counter = 1
while pos < length do
var c = self[pos]
var end_reached = false
if c == '[' then
counter += 1
out.add c
else if c == ']' then
counter -= 1
if counter == 0 then
end_reached = true
else
out.add c
end
else
out.add c
end
if end_reached then break
pos += 1
end
if pos == length then return -1
return pos
end
# Extract the XML tag name from a XML tag.
private fun xml_tag: String do
var tpl = new FlatBuffer
var pos = 1
if pos < length and self[1] == '/' then pos += 1
while pos < length - 1 and (self[pos].is_digit or self[pos].is_letter) do
tpl.add self[pos]
pos += 1
end
return tpl.write_to_string.to_lower
end
private fun is_valid_html_tag: Bool do
if is_empty then return false
for c in self do
if not c.is_alpha then return false
end
return true
end
# Read and escape the markdown contained in `self`.
private fun escape(out: FlatBuffer, c: Char, pos: Int): Int do
if c == '\\' or c == '[' or c == ']' or c == '(' or c == ')' or c == '{' or
c == '}' or c == '#' or c == '"' or c == '\'' or c == '.' or c == '<' or
c == '>' or c == '*' or c == '+' or c == '-' or c == '_' or c == '!' or
c == '`' or c == '~' or c == '^' then
out.add c
return pos + 1
end
out.add '\\'
return pos
end
# Extract string found at end of fence opening.
private fun meta_from_fence: nullable Text do
for i in [0..chars.length[ do
var c = chars[i]
if c != ' ' and c != '`' and c != '~' then
return substring_from(i).trim
end
end
return null
end
# Is `self` an unsafe HTML element?
private fun is_html_unsafe: Bool do return html_unsafe_tags.has(self.write_to_string)
# Is `self` a HRML block element?
private fun is_html_block: Bool do return html_block_tags.has(self.write_to_string)
# Is `self` a link prefix?
private fun is_link_prefix: Bool do return html_link_prefixes.has(self.write_to_string)
private fun html_unsafe_tags: Array[String] do return once ["applet", "head", "body", "frame", "frameset", "iframe", "script", "object"]
private fun html_block_tags: Array[String] do return once ["address", "article", "aside", "audio", "blockquote", "canvas", "dd", "div", "dl", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hgroup", "hr", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"]
private fun html_link_prefixes: Array[String] do return once ["http", "https", "ftp", "ftps"]
end
lib/markdown/markdown.nit:2333,1--2601,3
redef class Text
# Return `self` between `'`s, escaping `\` and `'`
#
# assert "'; DROP TABLE students".to_sql_string == "'''; DROP TABLE students'"
fun to_sql_string: String
do
return "'{self.replace('\\', "\\\\").replace('\'', "''")}'"
end
# Format the date represented by `self` into an escaped string for SQLite
#
# `self` must be composed of 1 to 3 integers separated by '-'.
# An incompatible format will result in an invalid date string.
#
# assert "2016-5-1".to_sql_date_string == "'2016-05-01'"
# assert "2016".to_sql_date_string == "'2016-01-01'"
fun to_sql_date_string: String
do
var parts = self.split("-")
for i in [parts.length .. 3[ do parts[i] = "1"
var year = parts[0].justify(4, 1.0, '0')
var month = parts[1].justify(2, 1.0, '0')
var day = parts[2].justify(2, 1.0, '0')
return "{year}-{month}-{day}".to_sql_string
end
end
lib/sqlite3/sqlite3.nit:323,1--350,3
redef class Text
# Execute a simple HTTP GET request to the URL `self`
#
# Set `accept_status_code` to the expected response HTTP code, defaults to 200.
# If a different status code is received, the return code is printed to stderr.
#
# Returns the response body on success and `null` on error. Prints the error
# message to stderr.
#
# For more control, set HTTP request headers, keep the response status code
# and much more, use `CurlHTTPRequest`.
#
# ~~~nitish
# assert "http://example.com/".http_get != null
# ~~~
fun http_get(accept_status_code: nullable Int): nullable String
do
var req = new CurlHTTPRequest(self.to_s)
var resp = req.execute
req.close
if resp isa CurlResponseSuccess then
if resp.status_code == (accept_status_code or else 200) then
return resp.body_str
else
print_error "HTTP request failed: server returned {resp.status_code}"
end
else if resp isa CurlResponseFailed then
print_error "HTTP request failed: {resp.error_msg}"
else abort
return null
end
# Download the file at URL `self` to `output_path` with a simple HTTP request
#
# If not set, `output_path` defaults to `self.basename`.
#
# Set `accept_status_code` to the expected response HTTP code, defaults to 200.
# If a different status code is received, the return code is printed to stderr.
#
# Returns the path to the downloaded file on success and `null` on errors.
# Prints the error message to stderr.
#
# For more control, set HTTP request headers, keep the response status code
# and much more, use `CurlHTTPRequest`.
#
# ~~~nitish
# assert "http://example.com/".http_download("index.html") == "example.com"
# ~~~
fun http_download(output_path: nullable Text, accept_status_code: nullable Int): nullable String
do
var path = (output_path or else self.basename).to_s
var req = new CurlHTTPRequest(self.to_s)
var resp = req.download_to_file(path)
req.close
if resp isa CurlFileResponseSuccess then
if resp.status_code == (accept_status_code or else 200) then
return path
else
print_error "HTTP request failed: server returned {resp.status_code}"
end
else if resp isa CurlResponseFailed then
print_error "HTTP request failed: {resp.error_msg}"
else abort
return null
end
end
lib/curl/extra.nit:20,1--89,3
redef class Text
# Does the operating system know the user named `self`?
fun user_exists: Bool
do
var passwd = new Passwd.from_name(to_s)
return not passwd.address_is_null
end
# Does the operating system know the group named `self`?
fun group_exists: Bool
do
var passwd = new Group.from_name(to_s)
return not passwd.address_is_null
end
end
lib/privileges/privileges.nit:26,1--40,3
redef class Text
# Get `self` as a `JavaString`
fun to_java_string: JavaString do return to_cstring.to_java_string
end
lib/java/ffi_support.nit:134,1--137,3
redef class Text super DirectSerializable end
lib/serialization/serialization_core.nit:264,1--45
redef class Text
redef fun open_in_browser do to_nsstring.native_open_in_browser
end
lib/ios/ui/ui.nit:619,1--621,3
redef class Text
# Strip the `nullable` prefix from the type name `self`
#
# ~~~
# assert "String".strip_nullable == "String"
# assert "nullable Array[Int]".strip_nullable == "Array[Int]"
# assert "Map[Set[String], Set[Int]]".strip_nullable == "Map[Set[String], Set[Int]]"
# ~~~
fun strip_nullable: Text
do
var prefix = "nullable "
return if has_prefix(prefix) then substring_from(prefix.length) else self
end
# Strip the `nullable` prefix and the params from the type name `self`
#
# ~~~
# assert "String".strip_nullable_and_params == "String"
# assert "nullable Array[Int]".strip_nullable_and_params == "Array"
# assert "Map[Set[String], Set[Int]]".strip_nullable_and_params == "Map"
# ~~~
fun strip_nullable_and_params: Text
do
var class_name = strip_nullable
var bracket_index = class_name.index_of('[')
if bracket_index == -1 then return class_name
return class_name.substring(0, bracket_index)
end
end
lib/serialization/engine_tools.nit:67,1--97,3
redef class Text
redef fun accept_json_serializer(v)
do
v.stream.write "\""
var start_i = 0
var escaped = null
for i in [0 .. self.length[ do
var char = self[i]
if char == '\\' then
escaped = "\\\\"
else if char == '\"' then
escaped = "\\\""
else if char < ' ' then
if char == '\n' then
escaped = "\\n"
else if char == '\r' then
escaped = "\\r"
else if char == '\t' then
escaped = "\\t"
else
escaped = char.escape_to_utf16
end
end
if escaped != null then
# Write open non-escaped string
if start_i <= i then
v.stream.write substring(start_i, i-start_i)
end
# Write escaped character
v.stream.write escaped
escaped = null
start_i = i+1
end
end
# Write remaining non-escaped string
if start_i < length then
if start_i == 0 then
v.stream.write self
else
v.stream.write substring(start_i, length-start_i)
end
end
v.stream.write "\""
end
end
lib/json/serialization_write.nit:147,1--197,3
redef class Text
# Tries to parse `self` as an S-Expression
fun to_sexp: SExpEntity do return (new SExpProcessor(self.to_s)).parse_entity
end
lib/sexp/sexp.nit:150,1--154,3
redef class Text
# Removes JSON-escaping if necessary in a JSON string
#
# assert "\\\"string\\uD83D\\uDE02\\\"".unescape_json == "\"string😂\""
fun unescape_json: Text do
if not json_need_escape then return self
return self.json_to_nit_string
end
# Does `self` need treatment from JSON to Nit ?
#
# i.e. is there at least one `\` character in it ?
#
# assert not "string".json_need_escape
# assert "\\\"string\\\"".json_need_escape
private fun json_need_escape: Bool do return has('\\')
# Escapes `self` from a JSON string to a Nit string
#
# assert "\\\"string\\\"".json_to_nit_string == "\"string\""
# assert "\\nEscape\\t\\n".json_to_nit_string == "\nEscape\t\n"
# assert "\\u0041zu\\uD800\\uDFD3".json_to_nit_string == "Azu𐏓"
private fun json_to_nit_string: String do
var res = new FlatBuffer.with_capacity(byte_length)
var i = 0
var ln = self.length
while i < ln do
var char = self[i]
if char == '\\' then
i += 1
char = self[i]
if char == 'b' then
char = 0x08.code_point
else if char == 'f' then
char = 0x0C.code_point
else if char == 'n' then
char = '\n'
else if char == 'r' then
char = '\r'
else if char == 't' then
char = '\t'
else if char == 'u' then
var u16_esc = from_utf16_digit(i + 1)
char = u16_esc.code_point
if char.is_surrogate and i + 10 < ln then
if self[i + 5] == '\\' and self[i + 6] == 'u' then
u16_esc <<= 16
u16_esc += from_utf16_digit(i + 7)
char = u16_esc.to_u32.from_utf16_surr.code_point
i += 6
else
char = 0xFFFD.code_point
end
end
i += 4
end
# `"`, `/` or `\` => Keep `char` as-is.
end
res.add char
i += 1
end
return res.to_s
end
# Parse `self` as JSON.
#
# If `self` is not a valid JSON document or contains an unsupported escape
# sequence, return a `JSONParseError`.
#
# Example with `JsonObject`:
#
# var obj = "\{\"foo\": \{\"bar\": true, \"goo\": [1, 2, 3]\}\}".parse_json
# assert obj isa JsonObject
# assert obj["foo"] isa JsonObject
# assert obj["foo"].as(JsonObject)["bar"] == true
#
# Example with `JsonArray`:
#
# var arr = "[1, 2, 3]".parse_json
# assert arr isa JsonArray
# assert arr.length == 3
# assert arr.first == 1
# assert arr.last == 3
#
# Example with `String`:
#
# var str = "\"foo, bar, baz\"".parse_json
# assert str isa String
# assert str == "foo, bar, baz"
#
# Example of a syntax error:
#
# var error = "\{foo: \"bar\"\}".parse_json
# assert error isa JsonParseError
# assert error.to_s == "Bad key format Error: bad JSON entity"
fun parse_json: nullable Serializable do return (new JSONStringParser(self.to_s)).parse_entity
end
lib/json/static.nit:28,1--125,3
redef class Text
# Parse `self` to a `JsonValue`
fun to_json_value: JsonValue do return new JsonValue(parse_json)
end
lib/json/dynamic.nit:25,1--28,3
redef class Text
redef fun accept_msgpack_serializer(v) do v.stream.write_msgpack_str self
end
lib/msgpack/serialization_write.nit:244,1--246,3
redef class Text
# Deserialize a `nullable Object` from this JSON formatted string
#
# If a `static_type` is given, only subtypes of the `static_type` are accepted.
#
# Warning: Deserialization errors are reported with `print_error` and
# may be returned as a partial object or as `null`.
#
# This method is not appropriate when errors need to be handled programmatically,
# manually use a `JsonDeserializer` in such cases.
fun deserialize_json(static_type: nullable String): nullable Object
do
var deserializer = new JsonDeserializer(self)
var res = deserializer.deserialize(static_type)
if deserializer.errors.not_empty then
print_error "Deserialization Errors: {deserializer.errors.join(", ")}"
end
return res
end
end
lib/json/serialization_read.nit:363,1--383,3
redef class Text
# Parse `self` as an XML BMFont description file
#
# Reports only basic XML format errors, other errors may be ignored or
# cause a crash.
#
# ~~~
# var desc = """
# <font>
# <info face="arial" size="72" bold="0" italic="0" charset=""
# unicode="1" stretchH="100" smooth="1" aa="1" padding="2,2,2,2"
# spacing="0,0" outline="0"/>
# <common lineHeight="80" base="65" scaleW="4030" scaleH="231"
# pages="1" packed="0"/>
# <pages>
# <page id="0" file="arial.png"/>
# </pages>
# <chars count="3">
# <char id="65" x="2519" y="10" width="55" height="59" xoffset="0"
# yoffset="13" xadvance="48" page="0" chnl="15"/>
# <char id="66" x="2600" y="10" width="46" height="58" xoffset="5"
# yoffset="13" xadvance="48" page="0" chnl="15"/>
# <char id="67" x="2673" y="9" width="52" height="60" xoffset="4"
# yoffset="12" xadvance="52" page="0" chnl="15"/>
# </chars>
# <kernings count="1">
# <kerning first="65" second="67" amount="-1"/>
# </kernings>
# </font>
# """
#
# var fnt = desc.parse_bmfont("dir_in_assets").value
# assert fnt.to_s == "<BMFont arial at 72.0 pt, 1 pages, 3 chars>"
# assert fnt.line_height == 80.0
# assert fnt.kernings['A', 'C'] == -1.0
# assert fnt.chars['A'].page.as(TextureAsset).path == "dir_in_assets/arial.png"
# ~~~
fun parse_bmfont(dir: String): MaybeError[BMFont, Error]
do
# Parse XML
var xml = to_xml
if xml isa XMLError then
var msg = "XML Parse Error: {xml.message}:{xml.location or else 0}"
return new MaybeError[BMFont, Error](maybe_error=new Error(msg))
end
# Basic sanity check
var roots = xml["font"]
if roots.is_empty then
var msg = "Error: the XML document doesn't declare the expected `font` root"
return new MaybeError[BMFont, Error](maybe_error=new Error(msg))
end
# Expect the rest of the document to be well formatted
var root = roots.first
var info = root["info"].first
assert info isa XMLAttrTag
var info_map = info.attributes_to_map
var common = root["common"].first
assert common isa XMLAttrTag
var common_map = common.attributes_to_map
var fnt = new BMFont(
info_map["face"],
info_map["size"].to_f,
info_map["bold"] == "1",
info_map["italic"] == "1",
info_map["unicode"] == "1",
info_map["padding"],
info_map["spacing"],
common_map["lineHeight"].to_f,
common_map["base"].to_f,
common_map["scaleW"].to_f,
common_map["scaleH"].to_f
)
# Pages / pixel data files
var xml_pages = root["pages"].first
for page in xml_pages["page"] do
if not page isa XMLAttrTag then continue
var attributes = page.attributes_to_map
var file = dir / attributes["file"]
fnt.pages[attributes["id"]] = new TextureAsset(file)
end
# Char description
for item in root["chars"].first["char"] do
if not item isa XMLAttrTag then continue
var attributes = item.attributes_to_map
var id = attributes["id"].to_i.code_point
var c = new BMFontChar(
attributes["x"].to_f, attributes["y"].to_f,
attributes["width"].to_f, attributes["height"].to_f,
attributes["xoffset"].to_f, attributes["yoffset"].to_f,
attributes["xadvance"].to_f,
fnt.pages[attributes["page"]])
fnt.chars[id] = c
end
# Kerning between two characters
var kernings = root["kernings"]
if kernings.not_empty then
for item in kernings.first["kerning"] do
if not item isa XMLAttrTag then continue
var attributes = item.attributes_to_map
var first = attributes["first"].to_i.code_point
var second = attributes["second"].to_i.code_point
var amount = attributes["amount"].to_f
fnt.kernings[first, second] = amount
end
end
return new MaybeError[BMFont, Error](fnt)
end
end
lib/gamnit/bmfont.nit:154,1--276,3
redef class Text
# Read `self` as raw text until `nend` and append it to the `out` buffer.
private fun read_until(out: FlatBuffer, start: Int, nend: Char...): Int do
var pos = start
while pos < length do
var c = self[pos]
var end_reached = false
for n in nend do
if c == n then
end_reached = true
break
end
end
if end_reached then break
out.add c
pos += 1
end
return pos
end
end
src/doc/commands/commands_parser.nit:473,1--492,3
redef class Text
# Execute an HTTP GET request synchronously at the URI `self`
#
# ~~~nitish
# var response = "http://example.org/".http_get
# if response.is_error then
# print_error response.error
# else
# print "HTTP status code: {response.code}"
# print response.value
# end
# ~~~
private fun http_get: HttpRequestResult is abstract
end
lib/app/http_request.nit:164,1--177,3
redef class Text
super Sendable
redef fun send(mpi, at, count, dest, tag, comm)
do
var str
if at != 0 or count != length then
str = substring(at, count)
else str = self
mpi.native_send(str.to_cstring, count, new DataType.char,
dest, tag, new Comm.world)
end
redef fun send_all(mpi, dest, tag, comm) do send(mpi, 0, length, dest, tag, comm)
end
lib/mpi/mpi.nit:419,1--434,3
redef class Text
redef fun http_get
do
var req = new CurlHTTPRequest(to_s)
var rep = req.execute
if rep isa CurlResponseSuccess then
return new HttpRequestResult(rep.body_str, null, rep.status_code)
else
assert rep isa CurlResponseFailed
var error = new IOError(rep.error_msg)
return new HttpRequestResult(null, error)
end
end
end
lib/linux/http_request.nit:26,1--39,3
redef class Text
redef fun open_in_browser do system("xdg-open '{self.escape_to_sh}' &")
end
lib/linux/ui.nit:345,1--347,3
redef class Text
# Read `self` between `nstart` and `nend` (excluded) and writte chars to `out`.
private fun read(out: FlatBuffer, nstart, nend: Int): Int do
var pos = nstart
while pos < length and pos < nend do
out.add self[pos]
pos += 1
end
if pos == length then return -1
return pos
end
end
src/doc/templates/html_commands.nit:448,1--459,3
redef class Text
redef fun http_get
do
var error_ref = new Ref[NSString]("Unknown Error".to_nsstring)
var data = to_nsstring.native_http_get(60.0, error_ref)
if data.address_is_null then
# There was an error
var error = new IOError(error_ref.item.to_s)
return new HttpRequestResult(null, error)
else
# TODO use the real return code instead of 200
return new HttpRequestResult(data.to_s, null, 200)
end
end
end
lib/ios/http_request.nit:32,1--47,3
redef class Text
redef fun open_in_browser
do to_java_string.native_open_in_browser(app.native_activity)
end
lib/android/ui/ui.nit:366,1--369,3
redef class Text
redef fun http_get
do
jni_env.push_local_frame 8
var juri = self.to_java_string
var jrep = java_http_get(juri)
assert not jrep.is_java_null
var res
if jrep.is_exception then
jrep = jrep.as_exception
# If the top exception doesn't have a message, get it from its causes.
var msg = null
var cause: JavaThrowable = jrep
loop
var jmsg = cause.message
if not jmsg.is_java_null then
msg = jmsg.to_s
break
else
cause = cause.cause
if cause.is_java_null then break
end
end
if msg == null then msg = jrep.to_s
res = new HttpRequestResult(null, new IOError(msg))
else if jrep.is_http_response then
jrep = jrep.as_http_response
res = new HttpRequestResult(jrep.content.to_s, null, jrep.status_code)
else abort
jni_env.pop_local_frame
return res
end
end
lib/android/http_request.nit:44,1--82,3