aboutsummaryrefslogtreecommitdiffstats
path: root/src
diff options
context:
space:
mode:
authorbptato <nincsnevem662@gmail.com>2024-11-24 13:02:15 +0100
committerbptato <nincsnevem662@gmail.com>2024-11-24 13:02:15 +0100
commitf07fb0d1f14a950a819c80d19cb52d05a566fb44 (patch)
treeb45c48531c8a36a236cc9bdb60eb5d4eab06fc13 /src
parent447d6d5cb4781e9b4c56ba08b7031ae9c10cd77b (diff)
downloadchawan-f07fb0d1f14a950a819c80d19cb52d05a566fb44.tar.gz
buffer: slightly improve markURL
merge text nodes, eat nobr, wbr
Diffstat (limited to 'src')
-rw-r--r--src/server/buffer.nim118
1 files changed, 69 insertions, 49 deletions
diff --git a/src/server/buffer.nim b/src/server/buffer.nim
index 120fd748..e89c486e 100644
--- a/src/server/buffer.nim
+++ b/src/server/buffer.nim
@@ -1647,59 +1647,79 @@ proc markURL*(buffer: Buffer; schemes: seq[string]) {.proxy.} =
var stack = @[buffer.document.body]
while stack.len > 0:
let element = stack.pop()
- for i in countdown(element.childList.high, 0):
- let node = element.childList[i]
+ var toRemove: seq[Node] = @[]
+ var texts: seq[Text] = @[]
+ var stackNext: seq[HTMLElement] = @[]
+ var lastText: Text = nil
+ for node in element.childList:
if node of Text:
let text = Text(node)
- var res = regex.exec(text.data)
- if res.success:
- var offset = 0
- var data = ""
- var j = 0
- for cap in res.captures.mitems:
- let capLen = cap[0].e - cap[0].s
- while j < cap[0].s:
- case (let c = text.data[j]; c)
- of '<':
- data &= "&lt;"
- offset += 3
- of '>':
- data &= "&gt;"
- offset += 3
- of '\'':
- data &= "&apos;"
- offset += 5
- of '"':
- data &= "&quot;"
- offset += 5
- of '&':
- data &= "&amp;"
- offset += 4
- else:
- data &= c
- inc j
- cap[0].s += offset
- cap[0].e += offset
- let s = text.data[j ..< j + capLen]
- let news = "<a href=\"" & s & "\">" & s.htmlEscape() & "</a>"
- data &= news
- j += cap[0].e - cap[0].s
- offset += news.len - (cap[0].e - cap[0].s)
- while j < text.data.len:
- case (let c = text.data[j]; c)
- of '<': data &= "&lt;"
- of '>': data &= "&gt;"
- of '\'': data &= "&apos;"
- of '"': data &= "&quot;"
- of '&': data &= "&amp;"
- else: data &= c
- inc j
- let replacement = html.fragmentParsingAlgorithm(data)
- discard element.replace(text, replacement)
+ if lastText != nil:
+ lastText.data &= text.data
+ toRemove.add(text)
+ else:
+ texts.add(text)
+ lastText = text
elif node of HTMLElement:
let element = HTMLElement(node)
- if element.tagType notin {TAG_HEAD, TAG_SCRIPT, TAG_STYLE, TAG_A}:
- stack.add(element)
+ if element.tagType in {TAG_NOBR, TAG_WBR}:
+ toRemove.add(node)
+ elif element.tagType notin {TAG_HEAD, TAG_SCRIPT, TAG_STYLE, TAG_A}:
+ stackNext.add(element)
+ lastText = nil
+ else:
+ lastText = nil
+ else:
+ lastText = nil
+ for it in toRemove:
+ it.remove()
+ for text in texts:
+ var res = regex.exec(text.data)
+ if res.success:
+ var offset = 0
+ var data = ""
+ var j = 0
+ for cap in res.captures.mitems:
+ let capLen = cap[0].e - cap[0].s
+ while j < cap[0].s:
+ case (let c = text.data[j]; c)
+ of '<':
+ data &= "&lt;"
+ offset += 3
+ of '>':
+ data &= "&gt;"
+ offset += 3
+ of '\'':
+ data &= "&apos;"
+ offset += 5
+ of '"':
+ data &= "&quot;"
+ offset += 5
+ of '&':
+ data &= "&amp;"
+ offset += 4
+ else:
+ data &= c
+ inc j
+ cap[0].s += offset
+ cap[0].e += offset
+ let s = text.data[j ..< j + capLen]
+ let news = "<a href=\"" & s & "\">" & s.htmlEscape() & "</a>"
+ data &= news
+ j += cap[0].e - cap[0].s
+ offset += news.len - (cap[0].e - cap[0].s)
+ while j < text.data.len:
+ case (let c = text.data[j]; c)
+ of '<': data &= "&lt;"
+ of '>': data &= "&gt;"
+ of '\'': data &= "&apos;"
+ of '"': data &= "&quot;"
+ of '&': data &= "&amp;"
+ else: data &= c
+ inc j
+ let replacement = html.fragmentParsingAlgorithm(data)
+ discard element.replace(text, replacement)
+ stack.add(stackNext)
buffer.reshape()
proc toggleImages0(buffer: Buffer): bool =