getting ready for 0.7

.travis.yml

@@ -3,14 +3,11 @@ language: julia
 os:
   - linux
 julia:
-  - 0.6
   - 0.7
   - 1.0
   - nightly
 matrix:
   allow_failures:
-  - julia: 0.7
-  - juila: 1
   - julia: nightly
 notifications:
   email: false

README.md

@@ -10,7 +10,7 @@ This package depends on the [Gumbo.jl](https://github.com/porterjamesj/Gumbo.jl)
 
 ### Usage
 
-Usage is simple. Use `Gumbo` to parse an HTML string into a document, create a `Selector` from a string, and then use `matchall` to get the nodes in the document that match the selector. Alternatively, use `sel"<selector string>"` to do the same thing as `Selector`. The `matchall` function returns an array of elements which match the selector. If no match is found, a zero element array is returned. For unique matches, the array contains one element. Thus, check the length of the array to test whether a selector matches.
+Usage is simple. Use `Gumbo` to parse an HTML string into a document, create a `Selector` from a string, and then use `eachmatch` to get the nodes in the document that match the selector. Alternatively, use `sel"<selector string>"` to do the same thing as `Selector`. The `eachmatch` function returns an array of elements which match the selector. If no match is found, a zero element array is returned. For unique matches, the array contains one element. Thus, check the length of the array to test whether a selector matches.
 
 ```julia
 using Cascadia
@@ -19,15 +19,17 @@ using Gumbo
 n=parsehtml("<p id=\"foo\"><p id=\"bar\">")
 s=Selector("#foo")
 sm = sel"#foo"
-matchall(s, n.root)
+eachmatch(s, n.root)
 # 1-element Array{Gumbo.HTMLNode,1}:
 #  Gumbo.HTMLElement{:p}
 
-matchall(sm, n.root)
+eachmatch(sm, n.root)
 # 1-element Array{Gumbo.HTMLNode,1}:
 #  Gumbo.HTMLElement{:p}
 ```
 
+__Note:__ The top level matching function name has changed from `matchall` in `v0.6` to `eachmatch` in `v0.7` and higher to reflect the change in Julia base.
+
 ### Webscraping Example
 
 The primary use case for this library is to enable webscraping -- the automatic extraction of information from html pages. As an example, consider the following code, which returns a list of questions that have been tagged with `julia-lang` on StackOverflow.
@@ -40,14 +42,14 @@ using Requests
 r = get("http://stackoverflow.com/questions/tagged/julia-lang")
 h = parsehtml(convert(String, r.data))
 
-qs = matchall(Selector(".question-summary"),h.root)
+qs = eachmatch(Selector(".question-summary"),h.root)
 
 println("StackOverflow Julia Questions (votes  answered?  url)")
 
 for q in qs
-    votes = nodeText(matchall(Selector(".votes .vote-count-post "), q)[1])
-    answered = length(matchall(Selector(".status.answered"), q)) > 0
-    href = matchall(Selector(".question-hyperlink"), q)[1].attributes["href"]
+    votes = nodeText(eachmatch(Selector(".votes .vote-count-post "), q)[1])
+    answered = length(eachmatch(Selector(".status.answered"), q)) > 0
+    href = eachmatch(Selector(".question-hyperlink"), q)[1].attributes["href"]
     println("$votes  $answered  http://stackoverflow.com$href")
 end
 ```

REQUIRE

@@ -1,3 +1,3 @@
-julia 0.6
+julia 0.7
 Gumbo
 AbstractTrees

appveyor.yml

@@ -1,9 +1,18 @@
 environment:
   matrix:
-  - JULIA_URL: "https://julialang-s3.julialang.org/bin/winnt/x86/0.4/julia-0.4-latest-win32.exe"
-  - JULIA_URL: "https://julialang-s3.julialang.org/bin/winnt/x64/0.4/julia-0.4-latest-win64.exe"
-  - JULIA_URL: "https://julialangnightlies-s3.julialang.org/bin/winnt/x86/julia-latest-win32.exe"
-  - JULIA_URL: "https://julialangnightlies-s3.julialang.org/bin/winnt/x64/julia-latest-win64.exe"
+  - julia_version: 0.7
+  - julia_version: 1
+  - julia_version: nightly
+
+platform:
+  - x86 # 32-bit
+  - x64 # 64-bit
+
+# # Uncomment the following lines to allow failures on nightly julia
+# # (tests will run but not make your overall status red)
+# matrix:
+allow_failures:
+  - julia_version: nightly
 
 branches:
   only:
@@ -17,19 +26,18 @@ notifications:
     on_build_status_changed: false
 
 install:
-  - ps: "[System.Net.ServicePointManager]::SecurityProtocol = [System.Net.SecurityProtocolType]::Tls12"
-# Download most recent Julia Windows binary
-  - ps: (new-object net.webclient).DownloadFile(
-        $env:JULIA_URL,
-        "C:\projects\julia-binary.exe")
-# Run installer silently, output to C:\projects\julia
-  - C:\projects\julia-binary.exe /S /D=C:\projects\julia
+  - ps: iex ((new-object net.webclient).DownloadString("https://raw.githubusercontent.com/JuliaCI/Appveyor.jl/version-1/bin/install.ps1"))
 
 build_script:
-# Need to convert from shallow to complete for Pkg.clone to work
-  - IF EXIST .git\shallow (git fetch --unshallow)
-  - C:\projects\julia\bin\julia -e "versioninfo();
-      Pkg.clone(pwd(), \"Cascadia\"); Pkg.build(\"Cascadia\")"
+  - echo "%JL_BUILD_SCRIPT%"
+  - C:\julia\bin\julia -e "%JL_BUILD_SCRIPT%"
 
 test_script:
-  - C:\projects\julia\bin\julia --check-bounds=yes -e "Pkg.test(\"Cascadia\")"
+  - echo "%JL_TEST_SCRIPT%"
+  - C:\julia\bin\julia -e "%JL_TEST_SCRIPT%"
+
+# # Uncomment to support code coverage upload. Should only be enabled for packages
+# # which would have coverage gaps without running on Windows
+# on_success:
+#   - echo "%JL_CODECOV_SCRIPT%"
+#   - C:\julia\bin\julia -e "%JL_CODECOV_SCRIPT%"

src/parser.jl

@@ -24,7 +24,7 @@ function parseEscape(p::Parser)
 	  while  i < p.i+6 && i <= length(p.s) && hexDigit(p.s[i])
 		  i += 1
 	  end
-	  v = parse(UInt, p.s[start:i], 16)
+	  v = parse(UInt, p.s[start:i], base=16)
 	  if length(p.s) >= i
 		  if  p.s[i] == '\r'
 			  i += 1
@@ -211,7 +211,7 @@ function skipWhitespace(p::Parser) #->boolean
 			continue
 		elseif p.s[i] == '/'
 			if startswith(p.s[p.i:end], "/*")
-				ends,endl = search(p.s, "*/", i+length("/*"))
+				ends,endl = something(findnext("*/", p.s, i+length("/*")), 0:-1)
 				if endl != -1
 					i = endl+1
 					continue

src/selector.jl

@@ -17,7 +17,7 @@ firstChild(n::HTMLDocument) = n.root
 function nextSibling(n::HTMLNode)
      p=n.parent
      l=length(p.children)
-     i=find(x->x===n, p.children)
+     i=findall(x->x===n, p.children)
      if isempty(i) || i[1]==l
          return nothing
      else
@@ -28,7 +28,7 @@ end
 function prevSibling(n::HTMLNode)
      p=n.parent
      l=length(p.children)
-     i=find(x->x===n, p.children)
+     i=findall(x->x===n, p.children)
      if isempty(i) || i[1]==1
          return nothing
      else
@@ -85,12 +85,18 @@ end
 # // MustCompile is like Compile, but panics instead of returning an error.
 
 
-#// MatchAll returns a slice of the nodes that match the selector,
+#// eachmatch returns a slice of the nodes that match the selector,
 #// from n and its children.
-function Base.matchall(s::Selector, n::HTMLNode ) #->HTMLNode[]
+function Base.eachmatch(s::Selector, n::HTMLNode ) #->HTMLNode[]
     return matchAllInto(s, n, HTMLNode[])
 end
 
+if VERSION >= v"0.7-" && VERSION < v"1.0-"
+function Base.matchall(s::Selector, n::HTMLNode )
+    Base.depwarn("use eachmatch instead of matchall", :matchall)
+    eachmatch(s, n)
+end
+end
 
 
 function matchAllInto(s::Selector, n::HTMLNode, storage::Array)
@@ -228,7 +234,7 @@ end
 #// the attribute named key contains val.
 function attributeSubstringSelector(key::AbstractString, val::AbstractString) #-> Selector
     return attributeSelector(key) do s
-        return contains(s, val)
+        return occursin(val, s)
     end
 end
 
@@ -238,7 +244,7 @@ end
 #// the attribute named key matches the regular expression rx
 function attributeRegexSelector(key::AbstractString, rx::Regex) #->Selector
     return attributeSelector(key) do s
-        return ismatch(rx, key)
+        return occursin(rx, key)
     end
 end
 
@@ -299,7 +305,7 @@ function nodeOwnText(n::HTMLNode) #->String
             write(b, c.text)
         end
     end
-    return takebuf_string(b)
+    return String(take!(copy(b)))
 end
 
 nodeOwnText(n::HTMLText) = ""
@@ -311,7 +317,7 @@ nodeOwnText(n::HTMLText) = ""
 function textSubstrSelector(val::AbstractString) #->Selector
     return Selector() do n::HTMLNode
         text = lowercase(nodeText(n))
-        return contains(text, val)
+        return occursin(val, text)
     end
 end
 
@@ -322,7 +328,7 @@ end
 function ownTextSubstrSelector(val::AbstractString) #->Selector
     return Selector() do n::HTMLNode
         text = lowercase(nodeOwnText(n))
-        return contains(text, val)
+        return occursin(val, text)
     end
 end
 
@@ -332,7 +338,7 @@ end
 #// the specified regular expression
 function textRegexSelector(rx::Regex) #->Selector
     return Selector() do n::HTMLNode
-        return ismatch(rx, nodeText(n))
+        return occursin(rx, nodeText(n))
     end
 end
 
@@ -342,7 +348,7 @@ end
 #// directly matches the specified regular expression
 function ownTextRegexSelector(rx::Regex) #->Selector
     return Selector() do n::HTMLNode
-        return ismatch(rx, nodeOwnText(n))
+        return occursin(rx, nodeOwnText(n))
     end
 end
 

test/runtests.jl

@@ -1,5 +1,5 @@
 using Cascadia
-using Base.Test
+using Test
 using JSON
 using Gumbo
 
@@ -40,11 +40,11 @@ for (i, d) in enumerate(selectorTests)
     c = Selector(d["Selector"])
     @test typeof(c) == Selector
     n=parsehtml(d["HTML"])
-    r=matchall(c, n.root)
+    r=eachmatch(c, n.root)
     l=length(r)
     e = length(d["Results"])
     if l != e
-        cnt += 1
+        global cnt += 1
         println("Test Failure (known) for $(d["Selector"]) Expected $e, got $l")
     else
         println("Test Success         for $(d["Selector"])")