Change capture upper bounds to inclusive
This commit is contained in:
parent
bdd8567f50
commit
4e83fc5867
5 changed files with 29 additions and 30 deletions
|
|
@ -118,11 +118,10 @@ at that id. If the value is invalid, then behavior is undefined. If the id is
|
||||||
- `"abc".match(re"(\w)\w").captures[-1] == "ab"`
|
- `"abc".match(re"(\w)\w").captures[-1] == "ab"`
|
||||||
`captureBounds[]: Option[Slice[int]]` :: gets the bounds of the
|
`captureBounds[]: Option[Slice[int]]` :: gets the bounds of the
|
||||||
given capture according to the same rules as the above. If the capture is not
|
given capture according to the same rules as the above. If the capture is not
|
||||||
filled, then `None` is returned. The upper bound is exclusive, the lower bound
|
filled, then `None` is returned. The bounds are both inclusive.
|
||||||
is inclusive.
|
- `"abc".match(re"(\w)").captureBounds[0] == 0 .. 0`
|
||||||
- `"abc".match(re"(\w)").captureBounds[0] == 0..1`
|
- `"abc".match(re"").captureBounds[-1] == 0 .. -1`
|
||||||
- `"abc".match(re"").captureBounds[-1] == 0..0`
|
- `"abc".match(re"abc").captureBounds[-1] == 0 .. 2`
|
||||||
- `"abc".match(re"abc").captureBounds[-1] == 0..3`
|
|
||||||
`match: string` :: the full text of the match.
|
`match: string` :: the full text of the match.
|
||||||
`matchBounds: Slice[int]` :: the bounds of the match, as in `captureBounds[]`
|
`matchBounds: Slice[int]` :: the bounds of the match, as in `captureBounds[]`
|
||||||
`(captureBounds|captures).toTable` :: returns a table with each named capture
|
`(captureBounds|captures).toTable` :: returns a table with each named capture
|
||||||
|
|
|
||||||
20
src/nre.nim
20
src/nre.nim
|
|
@ -97,7 +97,7 @@ proc `[]`*(pattern: CaptureBounds, i: int): Option[Slice[int]] =
|
||||||
let pattern = RegexMatch(pattern)
|
let pattern = RegexMatch(pattern)
|
||||||
if pattern.pcreMatchBounds[i + 1].a != -1:
|
if pattern.pcreMatchBounds[i + 1].a != -1:
|
||||||
let bounds = pattern.pcreMatchBounds[i + 1]
|
let bounds = pattern.pcreMatchBounds[i + 1]
|
||||||
return Some(int(bounds.a) .. int(bounds.b))
|
return Some(int(bounds.a) .. int(bounds.b-1))
|
||||||
else:
|
else:
|
||||||
return None[Slice[int]]()
|
return None[Slice[int]]()
|
||||||
|
|
||||||
|
|
@ -111,7 +111,7 @@ proc `[]`*(pattern: Captures, i: int): string =
|
||||||
|
|
||||||
if bounds:
|
if bounds:
|
||||||
let bounds = bounds.get
|
let bounds = bounds.get
|
||||||
return pattern.str.substr(bounds.a, bounds.b-1)
|
return pattern.str.substr(bounds.a, bounds.b)
|
||||||
else:
|
else:
|
||||||
return nil
|
return nil
|
||||||
|
|
||||||
|
|
@ -343,7 +343,7 @@ iterator findIter*(str: string, pattern: Regex, start = 0, endpos = -1): RegexMa
|
||||||
var flags = 0
|
var flags = 0
|
||||||
|
|
||||||
if match and
|
if match and
|
||||||
match.get.matchBounds.a == match.get.matchBounds.b:
|
match.get.matchBounds.a > match.get.matchBounds.b:
|
||||||
# 0-len match
|
# 0-len match
|
||||||
flags = pcre.NOTEMPTY_ATSTART or pcre.ANCHORED
|
flags = pcre.NOTEMPTY_ATSTART or pcre.ANCHORED
|
||||||
|
|
||||||
|
|
@ -363,7 +363,7 @@ iterator findIter*(str: string, pattern: Regex, start = 0, endpos = -1): RegexMa
|
||||||
offset += str.runeLenAt(offset)
|
offset += str.runeLenAt(offset)
|
||||||
assert(offset <= endpos)
|
assert(offset <= endpos)
|
||||||
else:
|
else:
|
||||||
offset = match.get.matchBounds.b
|
offset = match.get.matchBounds.b + 1
|
||||||
|
|
||||||
yield match.get
|
yield match.get
|
||||||
|
|
||||||
|
|
@ -387,7 +387,7 @@ proc split*(str: string, pattern: Regex, maxSplit = -1, start = 0): seq[string]
|
||||||
result = @[]
|
result = @[]
|
||||||
var lastIdx = start
|
var lastIdx = start
|
||||||
var splits = 0
|
var splits = 0
|
||||||
var bounds: Slice[int]
|
var bounds = 0 .. -1
|
||||||
|
|
||||||
for match in str.findIter(pattern, start = start):
|
for match in str.findIter(pattern, start = start):
|
||||||
# upper bound is exclusive, lower is inclusive:
|
# upper bound is exclusive, lower is inclusive:
|
||||||
|
|
@ -400,11 +400,11 @@ proc split*(str: string, pattern: Regex, maxSplit = -1, start = 0): seq[string]
|
||||||
# "12".split("") would be @["", "1", "2"], but
|
# "12".split("") would be @["", "1", "2"], but
|
||||||
# if we skip an empty first match, it's the correct
|
# if we skip an empty first match, it's the correct
|
||||||
# @["1", "2"]
|
# @["1", "2"]
|
||||||
if bounds.a < bounds.b or bounds.a > start:
|
if bounds.a <= bounds.b or bounds.a > start:
|
||||||
result.add(str.substr(lastIdx, bounds.a - 1))
|
result.add(str.substr(lastIdx, bounds.a - 1))
|
||||||
splits += 1
|
splits += 1
|
||||||
|
|
||||||
lastIdx = bounds.b
|
lastIdx = bounds.b + 1
|
||||||
|
|
||||||
for cap in match.captures:
|
for cap in match.captures:
|
||||||
# if there are captures, include them in the result
|
# if there are captures, include them in the result
|
||||||
|
|
@ -416,11 +416,11 @@ proc split*(str: string, pattern: Regex, maxSplit = -1, start = 0): seq[string]
|
||||||
# "12".split("\b") would be @["1", "2", ""], but
|
# "12".split("\b") would be @["1", "2", ""], but
|
||||||
# if we skip an empty last match, it's the correct
|
# if we skip an empty last match, it's the correct
|
||||||
# @["1", "2"]
|
# @["1", "2"]
|
||||||
if bounds.a < bounds.b or bounds.b < str.len:
|
if bounds.a <= bounds.b or bounds.b < str.high:
|
||||||
# last match: Each match takes the previous substring,
|
# last match: Each match takes the previous substring,
|
||||||
# but "1 2".split(/ /) needs to return @["1", "2"].
|
# but "1 2".split(/ /) needs to return @["1", "2"].
|
||||||
# This handles "2"
|
# This handles "2"
|
||||||
result.add(str.substr(bounds.b, str.len - 1))
|
result.add(str.substr(bounds.b + 1, str.high))
|
||||||
|
|
||||||
template replaceImpl(str: string, pattern: Regex,
|
template replaceImpl(str: string, pattern: Regex,
|
||||||
replacement: expr): stmt {.immediate, dirty.} =
|
replacement: expr): stmt {.immediate, dirty.} =
|
||||||
|
|
@ -435,7 +435,7 @@ template replaceImpl(str: string, pattern: Regex,
|
||||||
assert(nextVal != nil)
|
assert(nextVal != nil)
|
||||||
result.add(nextVal)
|
result.add(nextVal)
|
||||||
|
|
||||||
lastIdx = bounds.b
|
lastIdx = bounds.b + 1
|
||||||
|
|
||||||
result.add(str.substr(lastIdx, str.len - 1))
|
result.add(str.substr(lastIdx, str.len - 1))
|
||||||
return result
|
return result
|
||||||
|
|
|
||||||
|
|
@ -8,17 +8,17 @@ suite "captures":
|
||||||
|
|
||||||
test "capture bounds are correct":
|
test "capture bounds are correct":
|
||||||
let ex1 = re("([0-9])")
|
let ex1 = re("([0-9])")
|
||||||
check("1 23".find(ex1).matchBounds == 0 .. 1)
|
check("1 23".find(ex1).matchBounds == 0 .. 0)
|
||||||
check("1 23".find(ex1).captureBounds[0].get == 0 .. 1)
|
check("1 23".find(ex1).captureBounds[0].get == 0 .. 0)
|
||||||
check("1 23".find(ex1, 1).matchBounds == 2 .. 3)
|
check("1 23".find(ex1, 1).matchBounds == 2 .. 2)
|
||||||
check("1 23".find(ex1, 3).matchBounds == 3 .. 4)
|
check("1 23".find(ex1, 3).matchBounds == 3 .. 3)
|
||||||
|
|
||||||
let ex2 = re("()()()()()()()()()()([0-9])")
|
let ex2 = re("()()()()()()()()()()([0-9])")
|
||||||
check("824".find(ex2).captureBounds[0].get == 0 .. 0)
|
check("824".find(ex2).captureBounds[0].get == 0 .. -1)
|
||||||
check("824".find(ex2).captureBounds[10].get == 0 .. 1)
|
check("824".find(ex2).captureBounds[10].get == 0 .. 0)
|
||||||
|
|
||||||
let ex3 = re("([0-9]+)")
|
let ex3 = re("([0-9]+)")
|
||||||
check("824".find(ex3).captureBounds[0].get == 0 .. 3)
|
check("824".find(ex3).captureBounds[0].get == 0 .. 2)
|
||||||
|
|
||||||
test "named captures":
|
test "named captures":
|
||||||
let ex1 = "foobar".find(re("(?<foo>foo)(?<bar>bar)"))
|
let ex1 = "foobar".find(re("(?<foo>foo)(?<bar>bar)"))
|
||||||
|
|
@ -31,7 +31,7 @@ suite "captures":
|
||||||
|
|
||||||
test "named capture bounds":
|
test "named capture bounds":
|
||||||
let ex1 = "foo".find(re("(?<foo>foo)(?<bar>bar)?"))
|
let ex1 = "foo".find(re("(?<foo>foo)(?<bar>bar)?"))
|
||||||
check(ex1.captureBounds["foo"] == Some(0..3))
|
check(ex1.captureBounds["foo"] == Some(0..2))
|
||||||
check(ex1.captureBounds["bar"] == None[Slice[int]]())
|
check(ex1.captureBounds["bar"] == None[Slice[int]]())
|
||||||
|
|
||||||
test "capture count":
|
test "capture count":
|
||||||
|
|
@ -42,7 +42,7 @@ suite "captures":
|
||||||
test "named capture table":
|
test "named capture table":
|
||||||
let ex1 = "foo".find(re("(?<foo>foo)(?<bar>bar)?"))
|
let ex1 = "foo".find(re("(?<foo>foo)(?<bar>bar)?"))
|
||||||
check(ex1.captures.toTable == {"foo" : "foo", "bar" : nil}.toTable())
|
check(ex1.captures.toTable == {"foo" : "foo", "bar" : nil}.toTable())
|
||||||
check(ex1.captureBounds.toTable == {"foo" : Some(0..3), "bar" : None[Slice[int]]()}.toTable())
|
check(ex1.captureBounds.toTable == {"foo" : Some(0..2), "bar" : None[Slice[int]]()}.toTable())
|
||||||
check(ex1.captures.toTable("") == {"foo" : "foo", "bar" : ""}.toTable())
|
check(ex1.captures.toTable("") == {"foo" : "foo", "bar" : ""}.toTable())
|
||||||
|
|
||||||
let ex2 = "foobar".find(re("(?<foo>foo)(?<bar>bar)?"))
|
let ex2 = "foobar".find(re("(?<foo>foo)(?<bar>bar)?"))
|
||||||
|
|
@ -51,7 +51,7 @@ suite "captures":
|
||||||
test "capture sequence":
|
test "capture sequence":
|
||||||
let ex1 = "foo".find(re("(?<foo>foo)(?<bar>bar)?"))
|
let ex1 = "foo".find(re("(?<foo>foo)(?<bar>bar)?"))
|
||||||
check(ex1.captures.toSeq == @["foo", nil])
|
check(ex1.captures.toSeq == @["foo", nil])
|
||||||
check(ex1.captureBounds.toSeq == @[Some(0..3), None[Slice[int]]()])
|
check(ex1.captureBounds.toSeq == @[Some(0..2), None[Slice[int]]()])
|
||||||
check(ex1.captures.toSeq("") == @["foo", ""])
|
check(ex1.captures.toSeq("") == @["foo", ""])
|
||||||
|
|
||||||
let ex2 = "foobar".find(re("(?<foo>foo)(?<bar>bar)?"))
|
let ex2 = "foobar".find(re("(?<foo>foo)(?<bar>bar)?"))
|
||||||
|
|
|
||||||
|
|
@ -10,7 +10,7 @@ suite "find":
|
||||||
test "find bounds":
|
test "find bounds":
|
||||||
check(toSeq(findIter("1 2 3 4 5 ", re" ")).map(
|
check(toSeq(findIter("1 2 3 4 5 ", re" ")).map(
|
||||||
proc (a: RegexMatch): Slice[int] = a.matchBounds
|
proc (a: RegexMatch): Slice[int] = a.matchBounds
|
||||||
) == @[1..2, 3..4, 5..6, 7..8, 9..10])
|
) == @[1..1, 3..3, 5..5, 7..7, 9..9])
|
||||||
|
|
||||||
test "overlapping find":
|
test "overlapping find":
|
||||||
check("222".findAll(re"22") == @["22"])
|
check("222".findAll(re"22") == @["22"])
|
||||||
|
|
|
||||||
|
|
@ -9,9 +9,9 @@ suite "match":
|
||||||
check("abc".match(re"(\w)").captures[0] == "a")
|
check("abc".match(re"(\w)").captures[0] == "a")
|
||||||
check("abc".match(re"(?<letter>\w)").captures["letter"] == "a")
|
check("abc".match(re"(?<letter>\w)").captures["letter"] == "a")
|
||||||
check("abc".match(re"(\w)\w").captures[-1] == "ab")
|
check("abc".match(re"(\w)\w").captures[-1] == "ab")
|
||||||
check("abc".match(re"(\w)").captureBounds[0].get == 0..1)
|
check("abc".match(re"(\w)").captureBounds[0].get == 0 .. 0)
|
||||||
check("abc".match(re"").captureBounds[-1].get == 0..0)
|
check("abc".match(re"").captureBounds[-1].get == 0 .. -1)
|
||||||
check("abc".match(re"abc").captureBounds[-1].get == 0..3)
|
check("abc".match(re"abc").captureBounds[-1].get == 0 .. 2)
|
||||||
|
|
||||||
test "match test cases":
|
test "match test cases":
|
||||||
check("123".match(re"").matchBounds == 0..0)
|
check("123".match(re"").matchBounds == 0 .. -1)
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue