aphrody-labs/PowerShell
1
0 Fork 0
mirror of https://github.com/aphrody-labs/PowerShell.git synced 2026-10-17 12:45:47 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Initialize Regex lazy in BasicHtmlWebResponseObject (#19361)

Browse Source
This commit is contained in:
CarloToso authored and GitHub committed 2023-03-18 22:06:32 +05:00
1 parent 69e9b439fd
commit 688c7f3689
1 file changed
+22 -45
Download Patch File Download Diff File Expand all files Collapse all files
src/Microsoft.PowerShell.Commands.Utility/commands/utility/WebCmdlet/Common/BasicHtmlWebResponseObject.Common.cs
+22 -45
View File
@@ -16,17 +16,6 @@ namespace Microsoft.PowerShell.Commands
/// </summary>
public class BasicHtmlWebResponseObject : WebResponseObject
{
#region Private Fields
private static Regex s_attribNameValueRegex;
private static Regex s_attribsRegex;
private static Regex s_imageRegex;
private static Regex s_inputFieldRegex;
private static Regex s_linkRegex;
private static Regex s_tagRegex;
#endregion Private Fields
#region Constructors
/// <summary>
@@ -43,7 +32,6 @@ namespace Microsoft.PowerShell.Commands
/// <param name="contentStream"></param>
public BasicHtmlWebResponseObject(HttpResponseMessage response, Stream contentStream) : base(response, contentStream)
{
EnsureHtmlParser();
InitializeContent();
InitializeRawContent(response);
}
@@ -82,10 +70,8 @@ namespace Microsoft.PowerShell.Commands
{
if (_inputFields == null)
{
EnsureHtmlParser();
List<PSObject> parsedFields = new();
MatchCollection fieldMatch = s_inputFieldRegex.Matches(Content);
MatchCollection fieldMatch = HtmlParser.InputFieldRegex.Matches(Content);
foreach (Match field in fieldMatch)
{
parsedFields.Add(CreateHtmlObject(field.Value, "INPUT"));
@@ -109,10 +95,8 @@ namespace Microsoft.PowerShell.Commands
{
if (_links == null)
{
EnsureHtmlParser();
List<PSObject> parsedLinks = new();
MatchCollection linkMatch = s_linkRegex.Matches(Content);
MatchCollection linkMatch = HtmlParser.LinkRegex.Matches(Content);
foreach (Match link in linkMatch)
{
parsedLinks.Add(CreateHtmlObject(link.Value, "A"));
@@ -136,10 +120,8 @@ namespace Microsoft.PowerShell.Commands
{
if (_images == null)
{
EnsureHtmlParser();
List<PSObject> parsedImages = new();
MatchCollection imageMatch = s_imageRegex.Matches(Content);
MatchCollection imageMatch = HtmlParser.ImageRegex.Matches(Content);
foreach (Match image in imageMatch)
{
parsedImages.Add(CreateHtmlObject(image.Value, "IMG"));
@@ -188,27 +170,6 @@ namespace Microsoft.PowerShell.Commands
return elementObject;
}
private static void EnsureHtmlParser()
{
s_tagRegex ??= new Regex(@"<\w+((\s+[^""'>/=\s\p{Cc}]+(\s*=\s*(?:"".*?""|'.*?'|[^'"">\s]+))?)+\s*|\s*)/?>",
RegexOptions.Singleline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
s_attribsRegex ??= new Regex(@"(?<=\s+)([^""'>/=\s\p{Cc}]+(\s*=\s*(?:"".*?""|'.*?'|[^'"">\s]+))?)",
RegexOptions.Singleline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
s_attribNameValueRegex ??= new Regex(@"([^""'>/=\s\p{Cc}]+)(?:\s*=\s*(?:""(.*?)""|'(.*?)'|([^'"">\s]+)))?",
RegexOptions.Singleline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
s_inputFieldRegex ??= new Regex(@"<input\s+[^>]*(/?>|>.*?</input>)",
RegexOptions.Singleline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
s_linkRegex ??= new Regex(@"<a\s+[^>]*(/>|>.*?</a>)",
RegexOptions.Singleline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
s_imageRegex ??= new Regex(@"<img\s[^>]*?>",
RegexOptions.Singleline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
}
private void InitializeRawContent(HttpResponseMessage baseResponse)
{
StringBuilder raw = ContentHelper.GetRawContentHeader(baseResponse);
@@ -223,16 +184,16 @@ namespace Microsoft.PowerShell.Commands
{
// Extract just the opening tag of the HTML element (omitting the closing tag and any contents,
// including contained HTML elements)
Match match = s_tagRegex.Match(outerHtml);
Match match = HtmlParser.TagRegex.Match(outerHtml);
// Extract all the attribute specifications within the HTML element opening tag
MatchCollection attribMatches = s_attribsRegex.Matches(match.Value);
MatchCollection attribMatches = HtmlParser.AttribsRegex.Matches(match.Value);
foreach (Match attribMatch in attribMatches)
{
// Extract the name and value for this attribute (allowing for variations like single/double/no
// quotes, and no value at all)
Match nvMatches = s_attribNameValueRegex.Match(attribMatch.Value);
Match nvMatches = HtmlParser.AttribNameValueRegex.Match(attribMatch.Value);
Debug.Assert(nvMatches.Groups.Count == 5);
// Name is always captured by group #1
@@ -259,5 +220,21 @@ namespace Microsoft.PowerShell.Commands
}
#endregion Methods
// This class is needed so the static Regexes are initialized only the first time they are used
private static class HtmlParser
{
internal static readonly Regex AttribsRegex = new Regex(@"(?<=\s+)([^""'>/=\s\p{Cc}]+(\s*=\s*(?:"".*?""|'.*?'|[^'"">\s]+))?)", RegexOptions.Singleline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
internal static readonly Regex AttribNameValueRegex = new Regex(@"([^""'>/=\s\p{Cc}]+)(?:\s*=\s*(?:""(.*?)""|'(.*?)'|([^'"">\s]+)))?", RegexOptions.Singleline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
internal static readonly Regex ImageRegex = new Regex(@"<img\s[^>]*?>", RegexOptions.Singleline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
internal static readonly Regex InputFieldRegex = new Regex(@"<input\s+[^>]*(/?>|>.*?</input>)", RegexOptions.Singleline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
internal static readonly Regex LinkRegex = new Regex(@"<a\s+[^>]*(/>|>.*?</a>)", RegexOptions.Singleline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
internal static readonly Regex TagRegex = new Regex(@"<\w+((\s+[^""'>/=\s\p{Cc}]+(\s*=\s*(?:"".*?""|'.*?'|[^'"">\s]+))?)+\s*|\s*)/?>", RegexOptions.Singleline | RegexOptions.IgnoreCase | RegexOptions.Compiled);
}
}
}