ffilewatch 0.6.0 → 0.6.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 211f6275bcf6037d2e6379dd206e268ebbf77362
-  data.tar.gz: b329672228fc6ddd30802abae8803f550d7e84a1
+  metadata.gz: 07a481af51457dff387bdf3cb7d33fe0dbe056bd
+  data.tar.gz: 60d50fa77dba07d4faf31526e2aa56be0a4ff663
 SHA512:
-  metadata.gz: f9d01a57ce62ab9737847fc61ca14e98f17656ec0d0f1c2db52d3024fd86f56d33f2bf30e13d20de272fff75d38db07c345244463def7bb894fdb2e87ce3f9d1
-  data.tar.gz: 61084794c8ffdc1866c4c6b8cb23f94118a8ec92de05c6caffe6f0daa5238382890e71b848f729c3241fdb7e2b31b177f1eef270a521cc5e1994ca26929808ac
+  metadata.gz: 31810de1925838adb880afe3de1cd5ff465e87430f738f29d0ef9ea06b91d914e95b56a541ea97472a2b87f34bd92495b4670fc7baa4cc2d82208714b0b4c225
+  data.tar.gz: 59fcaef74a58f8e03d3b4035c093e5fc314ba3043be58aa7918422c965e6bcc21ae9e13456332809589181be44699649aab28c77b71d2979ff4bd6150ae9bbad

data/lib/filewatch/tail.rb

@@ -1,8 +1,5 @@
-require "filewatch/buftok"
+require 'buftok'
 require "filewatch/watch"
-if RbConfig::CONFIG['host_os'] =~ /mswin|mingw|cygwin/
-  require "filewatch/winhelper"
-end
 require "logger"
 require "rbconfig"
 
@@ -21,8 +18,6 @@ module FileWatch
 
     public
     def initialize(opts={})
-      @iswindows = ((RbConfig::CONFIG['host_os'] =~ /mswin|mingw|cygwin/) != nil)
-
       if opts[:logger]
         @logger = opts[:logger]
       else
@@ -43,7 +38,7 @@ module FileWatch
       @sincedb_writing = false
       @statcache = {}
       @opts = {
-        :eviction_interval => 60,
+        :eviction_interval => 300, # Let go of file handles after five minutes
         :sincedb_write_interval => 10,
         :stat_interval => 1,
         :discover_interval => 5,
@@ -81,7 +76,7 @@ module FileWatch
                        @opts[:discover_interval]) do |event, path|
         case event
         when :create, :create_initial
-          if @files.member?(path)
+          if @files[path].nil?
             @logger.debug("#{event} for #{path}: already exists in @files")
             next
           end
@@ -89,7 +84,7 @@ module FileWatch
             _read_file(path, &block)
           end
         when :modify
-          if !@files.member?(path)
+          if @files[path].nil?
             @logger.debug(":modify for #{path}, does not exist in @files")
             if _open_file(path, event)
               _read_file(path, &block)
@@ -117,11 +112,7 @@ module FileWatch
       @logger.debug("_open_file: #{path}: opening")
       @locked[path] = true
       begin
-        if @iswindows && defined? JRUBY_VERSION
-            @files[path] = Java::RubyFileExt::getRubyFile(path)
-        else
-            @files[path] = File.open(path)
-        end
+        @files[path] = File.open(path)
       rescue
         # don't emit this message too often. if a file that we can't
         # read is changing a lot, we'll try to open it more often,
@@ -148,12 +139,7 @@ module FileWatch
         # construct the inode key using the path which will be 'stable'
         inode = [path, stat.dev_major, stat.dev_minor]
       else
-        if @iswindows
-          fileId = Winhelper.GetWindowsUniqueFileIdentifier(path)
-          inode = [fileId, stat.dev_major, stat.dev_minor]
-        else
-          inode = [stat.ino.to_s, stat.dev_major, stat.dev_minor]
-        end
+        inode = [stat.ino.to_s, stat.dev_major, stat.dev_minor]
       end
 
       @statcache[path] = inode
@@ -191,7 +177,7 @@ module FileWatch
     private
     def _read_file(path, &block)
       @locked[path] = true
-      @buffers[path] ||= FileWatch::BufferedTokenizer.new
+      @buffers[path] ||= ::BufferedTokenizer.new
 
       changed = false
       loop do
@@ -319,20 +305,22 @@ module FileWatch
 
     private
     def _start_eviction
+      sleep_interval = 5
+      sleep_interval = 10 if @opts[:eviction_interval] >= 100
       @evict = Thread.new do
         loop do
           now = Time.now.to_i
           @changed.keys.each do |path|
             next if now - @changed[path] < @opts[:eviction_interval]
             next if @locked[path]
-            next unless @files.include?(path)
+            next if @files[path].nil?
             @logger.debug(":evict for #{path}, deleted from @files")
             @files.delete(path).close
             @statcache.delete(path)
             @changed.delete(path)
             @locked.delete(path)
           end
-          sleep 5
+          sleep sleep_interval
         end
       end
     end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ffilewatch
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.6.1
 platform: ruby
 authors:
 - Jordan Sissel
@@ -9,8 +9,22 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-08-05 00:00:00.000000000 Z
-dependencies: []
+date: 2014-08-06 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: buftok
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0'
 description: Watch files and directories in ruby. Also supports tailing and glob file
   patterns.
 email:
@@ -22,10 +36,8 @@ extra_rdoc_files: []
 files:
 - bin/globtail
 - lib/JRubyFileExtension.jar
-- lib/filewatch/buftok.rb
 - lib/filewatch/tail.rb
 - lib/filewatch/watch.rb
-- lib/filewatch/winhelper.rb
 - test/filewatch/tail.rb
 - test/globtail/Makefile
 - test/globtail/framework.sh

data/lib/filewatch/buftok.rb

@@ -1,139 +0,0 @@
-# BufferedTokenizer - Statefully split input data by a specifiable token
-#
-# Authors:: Tony Arcieri, Martin Emde
-#
-#----------------------------------------------------------------------------
-#
-# Copyright (C) 2006-07 by Tony Arcieri and Martin Emde
-# 
-# Distributed under the Ruby license (http://www.ruby-lang.org/en/LICENSE.txt)
-#
-#---------------------------------------------------------------------------
-#
-
-# (C)2006 Tony Arcieri, Martin Emde
-# Distributed under the Ruby license (http://www.ruby-lang.org/en/LICENSE.txt)
-
-# BufferedTokenizer takes a delimiter upon instantiation, or acts line-based
-# by default.  It allows input to be spoon-fed from some outside source which
-# receives arbitrary length datagrams which may-or-may-not contain the token
-# by which entities are delimited.
-#
-# Commonly used to parse lines out of incoming data:
-#
-#  module LineBufferedConnection
-#    def receive_data(data)
-#      (@buffer ||= BufferedTokenizer.new).extract(data).each do |line|
-#        receive_line(line)
-#      end
-#    end
-#  end
-
-module FileWatch; class BufferedTokenizer
-  # New BufferedTokenizers will operate on lines delimited by "\n" by default
-  # or allow you to specify any delimiter token you so choose, which will then
-  # be used by String#split to tokenize the input data
-  def initialize(delimiter = "\n", size_limit = nil)
-    # Store the specified delimiter
-    @delimiter = delimiter
-
-    # Store the specified size limitation
-    @size_limit = size_limit
-
-    # The input buffer is stored as an array.  This is by far the most efficient
-    # approach given language constraints (in C a linked list would be a more
-    # appropriate data structure).  Segments of input data are stored in a list
-    # which is only joined when a token is reached, substantially reducing the
-    # number of objects required for the operation.
-    @input = []
-
-    # Size of the input buffer
-    @input_size = 0
-  end
-
-  # Extract takes an arbitrary string of input data and returns an array of
-  # tokenized entities, provided there were any available to extract.  This
-  # makes for easy processing of datagrams using a pattern like:
-  #
-  #   tokenizer.extract(data).map { |entity| Decode(entity) }.each do ...
-  def extract(data)
-    # Extract token-delimited entities from the input string with the split command.
-    # There's a bit of craftiness here with the -1 parameter.  Normally split would
-    # behave no differently regardless of if the token lies at the very end of the 
-    # input buffer or not (i.e. a literal edge case)  Specifying -1 forces split to
-    # return "" in this case, meaning that the last entry in the list represents a
-    # new segment of data where the token has not been encountered
-    entities = data.split @delimiter, -1
-
-    # Check to see if the buffer has exceeded capacity, if we're imposing a limit
-    if @size_limit
-      raise 'input buffer full' if @input_size + entities.first.size > @size_limit
-      @input_size += entities.first.size
-    end
-    
-    # Move the first entry in the resulting array into the input buffer.  It represents
-    # the last segment of a token-delimited entity unless it's the only entry in the list.
-    @input << entities.shift
-
-    # If the resulting array from the split is empty, the token was not encountered
-    # (not even at the end of the buffer).  Since we've encountered no token-delimited
-    # entities this go-around, return an empty array.
-    return [] if entities.empty?
-
-    # At this point, we've hit a token, or potentially multiple tokens.  Now we can bring
-    # together all the data we've buffered from earlier calls without hitting a token,
-    # and add it to our list of discovered entities.
-    entities.unshift @input.join
-
-=begin
-    # Note added by FC, 10Jul07. This paragraph contains a regression. It breaks
-    # empty tokens. Think of the empty line that delimits an HTTP header. It will have
-    # two "\n" delimiters in a row, and this code mishandles the resulting empty token.
-    # It someone figures out how to fix the problem, we can re-enable this code branch.
-    # Multi-chara
-cter token support.
-    # Split any tokens that were incomplete on the last iteration buf complete now.
-    entities.map! do |e|
-      e.split @delimiter, -1
-    end
-    # Flatten the resulting array.  This has the side effect of removing the empty
-    # entry at the end that was produced by passing -1 to split.  Add it again if
-    # necessary.
-    if (entities[-1] == [])
-      entities.flatten! << []
-    else
-      entities.flatten!
-    end
-=end
-
-    # Now that we've hit a token, joined the input buffer and added it to the entities
-    # list, we can go ahead and clear the input buffer.  All of the segments that were
-    # stored before the join can now be garbage collected.
-    @input.clear
-    
-    # The last entity in the list is not token delimited, however, thanks to the -1
-    # passed to split.  It represents the beginning of a new list of as-yet-untokenized  
-    # data, so we add it to the start of the list.
-    @input << entities.pop
-    
-    # Set the new input buffer size, provided we're keeping track
-    @input_size = @input.first.size if @size_limit
-
-    # Now we're left with the list of extracted token-delimited entities we wanted
-    # in the first place.  Hooray!
-    entities
-  end
-  
-  # Flush the contents of the input buffer, i.e. return the input buffer even though
-  # a token has not yet been encountered
-  def flush
-    buffer = @input.join
-    @input.clear
-    buffer
-  end
-
-  # Is the buffer empty?
-  def empty?
-    @input.empty?
-  end
-end; end

data/lib/filewatch/winhelper.rb

@@ -1,70 +0,0 @@
-require "ffi"
-	
-module Winhelper
-	extend FFI::Library
-	
-	ffi_lib 'kernel32'
-	ffi_convention :stdcall
-	class FileTime < FFI::Struct
-		layout :lowDateTime, :uint,
-		:highDateTime, :uint
-	end
-	
-	#http://msdn.microsoft.com/en-us/library/windows/desktop/aa363788(v=vs.85).aspx
-	class FileInformation < FFI::Struct
-		def initialize()
-			createTime = FileTime.new
-			lastAccessTime = FileTime.new
-			lastWriteTime = FileTime.new
-		end
-		
-		layout :fileAttributes, :uint, #DWORD    dwFileAttributes;
-		:createTime, FileTime,  #FILETIME ftCreationTime;
-		:lastAccessTime, FileTime, #FILETIME ftLastAccessTime;
-		:lastWriteTime, FileTime, #FILETIME ftLastWriteTime;
-		:volumeSerialNumber, :uint, #DWORD    dwVolumeSerialNumber;
-		:fileSizeHigh, :uint, #DWORD    nFileSizeHigh;
-		:fileSizeLow, :uint, #DWORD    nFileSizeLow;
-		:numberOfLinks, :uint, #DWORD    nNumberOfLinks;
-		:fileIndexHigh, :uint, #DWORD    nFileIndexHigh;
-		:fileIndexLow, :uint #DWORD    nFileIndexLow;
-	end
-		
-	
-	#http://msdn.microsoft.com/en-us/library/windows/desktop/aa363858(v=vs.85).aspx
-	#HANDLE WINAPI CreateFile(_In_ LPCTSTR lpFileName,_In_  DWORD dwDesiredAccess,_In_ DWORD dwShareMode,
-	#						_In_opt_  LPSECURITY_ATTRIBUTES lpSecurityAttributes,_In_  DWORD dwCreationDisposition,
-	#						_In_      DWORD dwFlagsAndAttributes,_In_opt_  HANDLE hTemplateFile);
-	attach_function :GetOpenFileHandle, :CreateFileA, [:pointer, :uint, :uint, :pointer, :uint, :uint, :pointer], :pointer	
-	
-	#http://msdn.microsoft.com/en-us/library/windows/desktop/aa364952(v=vs.85).aspx
-	#BOOL WINAPI GetFileInformationByHandle(_In_   HANDLE hFile,_Out_  LPBY_HANDLE_FILE_INFORMATION lpFileInformation);
-	attach_function :GetFileInformationByHandle, [:pointer, :pointer], :int
-	
-	attach_function :CloseHandle, [:pointer], :int
-	
-	
-	def self.GetWindowsUniqueFileIdentifier(path)
-		handle = GetOpenFileHandle(path, 0, 7, nil, 3, 128, nil)
-		fileInfo = Winhelper::FileInformation.new
-		success = GetFileInformationByHandle(handle, fileInfo)
-		CloseHandle(handle)
-		if  success == 1
-			#args = [
-			#		fileInfo[:fileAttributes], fileInfo[:volumeSerialNumber], fileInfo[:fileSizeHigh], fileInfo[:fileSizeLow], 
-			#		fileInfo[:numberOfLinks], fileInfo[:fileIndexHigh], fileInfo[:fileIndexLow]
-			#	]
-			#p "Information: %u %u %u %u %u %u %u " % args
-			#this is only guaranteed on NTFS, for ReFS on windows 2012, GetFileInformationByHandleEx should be used with FILE_ID_INFO, which returns a 128 bit identifier
-			return "#{fileInfo[:volumeSerialNumber]}-#{fileInfo[:fileIndexLow]}-#{fileInfo[:fileIndexHigh]}"
-		else
-			#p "cannot retrieve file information, returning path"
-			return path;
-		end
-	end
-end
-
-#fileId = Winhelper.GetWindowsUniqueFileIdentifier('C:\inetpub\logs\LogFiles\W3SVC1\u_ex1fdsadfsadfasdf30612.log')
-#p "FileId: " + fileId
-#p "outside function, sleeping"
-#sleep(10)