taps-taps 0.3.24

data/lib/taps/utils.rb

@@ -0,0 +1,182 @@
+require 'zlib'
+require 'stringio'
+require 'time'
+require 'tempfile'
+require 'rest_client'
+
+require 'taps/errors'
+require 'taps/chunksize'
+
+module Taps
+module Utils
+  extend self
+
+  def windows?
+    return @windows if defined?(@windows)
+    require 'rbconfig'
+    @windows = !!(::Config::CONFIG['host_os'] =~ /mswin|mingw/)
+  end
+
+  def bin(cmd)
+    cmd = "#{cmd}.cmd" if windows?
+    cmd
+  end
+
+  def checksum(data)
+    Zlib.crc32(data)
+  end
+
+  def valid_data?(data, crc32)
+    Zlib.crc32(data) == crc32.to_i
+  end
+
+  def base64encode(data)
+    [data].pack("m")
+  end
+
+  def base64decode(data)
+    data.unpack("m").first
+  end
+
+  def format_data(data, opts={})
+    return {} if data.size == 0
+    string_columns = opts[:string_columns] || []
+    schema = opts[:schema] || []
+    table  = opts[:table]
+
+    max_lengths = schema.inject({}) do |hash, (column, meta)|
+      if meta[:db_type] =~ /^varchar\((\d+)\)/
+        hash.update(column => $1.to_i)
+      end
+      hash
+    end
+
+    header = data[0].keys
+    only_data = data.collect do |row|
+      row = blobs_to_string(row, string_columns)
+      row.each do |column, data|
+        if data.to_s.length > (max_lengths[column] || data.to_s.length)
+          raise Taps::InvalidData.new(<<-ERROR)
+Detected data that exceeds the length limitation of its column. This is
+generally due to the fact that SQLite does not enforce length restrictions.
+
+Table  : #{table}
+Column : #{column}
+Type   : #{schema.detect{|s| s.first == column}.last[:db_type]}
+Data   : #{data}
+          ERROR
+        end
+      end
+      header.collect { |h| row[h] }
+    end
+    { :header => header, :data => only_data }
+  end
+
+  # mysql text and blobs fields are handled the same way internally
+  # this is not true for other databases so we must check if the field is
+  # actually text and manually convert it back to a string
+  def incorrect_blobs(db, table)
+    return [] if (db.url =~ /mysql:\/\//).nil?
+
+    columns = []
+    db.schema(table).each do |data|
+      column, cdata = data
+      columns << column if cdata[:db_type] =~ /text/
+    end
+    columns
+  end
+
+  def blobs_to_string(row, columns)
+    return row if columns.size == 0
+    columns.each do |c|
+      row[c] = row[c].to_s if row[c].kind_of?(Sequel::SQL::Blob)
+    end
+    row
+  end
+
+  def calculate_chunksize(old_chunksize)
+    c = Taps::Chunksize.new(old_chunksize)
+
+    begin
+      c.start_time = Time.now
+      c.time_in_db = yield c
+    rescue Errno::EPIPE, RestClient::RequestFailed, RestClient::RequestTimeout
+      c.retries += 1
+      raise if c.retries > 2
+
+      # we got disconnected, the chunksize could be too large
+      # reset the chunksize based on the number of retries
+      c.reset_chunksize
+      retry
+    end
+
+    c.end_time = Time.now
+    c.calc_new_chunksize
+  end
+
+  def load_schema(database_url, schema_data)
+    Tempfile.open('taps') do |tmp|
+      File.open(tmp.path, 'w') { |f| f.write(schema_data) }
+      schema_bin(:load, database_url, tmp.path)
+    end
+  end
+
+  def load_indexes(database_url, index_data)
+    Tempfile.open('taps') do |tmp|
+      File.open(tmp.path, 'w') { |f| f.write(index_data) }
+      schema_bin(:load_indexes, database_url, tmp.path)
+    end
+  end
+
+  def schema_bin(*args)
+    bin_path = File.expand_path("#{File.dirname(__FILE__)}/../../bin/#{bin('schema')}")
+    `"#{bin_path}" #{args.map { |a| "'#{a}'" }.join(' ')}`
+  end
+
+  def primary_key(db, table)
+    db.schema(table).select { |c| c[1][:primary_key] }.map { |c| c[0] }
+  end
+
+  def single_integer_primary_key(db, table)
+    table = table.to_sym.identifier unless table.kind_of?(Sequel::SQL::Identifier)
+    keys = db.schema(table).select { |c| c[1][:primary_key] and c[1][:type] == :integer }
+    not keys.nil? and keys.size == 1
+  end
+
+  def order_by(db, table)
+    pkey = primary_key(db, table)
+    if pkey
+      pkey.kind_of?(Array) ? pkey : [pkey.to_sym]
+    else
+      table = table.to_sym.identifier unless table.kind_of?(Sequel::SQL::Identifier)
+      db[table].columns
+    end
+  end
+
+
+  # try to detect server side errors to
+  # give the client a more useful error message
+  def server_error_handling(&blk)
+    begin
+      blk.call
+    rescue Sequel::DatabaseError => e
+      if e.message =~ /duplicate key value/i
+        raise Taps::DuplicatePrimaryKeyError, e.message
+      else
+        raise
+      end
+    end
+  end
+
+  def reraise_server_exception(e)
+    if e.kind_of?(RestClient::Exception)
+      if e.respond_to?(:response) && e.response.headers[:content_type] == 'application/json'
+        json = OkJson.decode(e.response.to_s)
+        klass = eval(json['error_class']) rescue nil
+        raise klass.new(json['error_message'], :backtrace => json['error_backtrace']) if klass
+      end
+    end
+    raise e
+  end
+end
+end

data/lib/taps/version.rb

@@ -0,0 +1,18 @@
+require "yaml"
+
+module Taps
+  def self.version_yml
+    @@version_yml ||= YAML.load(File.read(File.dirname(__FILE__) + '/../../VERSION.yml'))
+  end
+
+  def self.version
+    version = "#{version_yml[:major]}.#{version_yml[:minor]}.#{version_yml[:patch]}"
+    version += ".#{version_yml[:build]}" if version_yml[:build]
+    version
+  end
+
+  def self.compatible_version
+    "#{version_yml[:major]}.#{version_yml[:minor]}"
+  end
+end
+

data/lib/vendor/okjson.rb

@@ -0,0 +1,555 @@
+# Copyright 2011 Keith Rarick
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+# THE SOFTWARE.
+
+# See https://github.com/kr/okjson for updates.
+
+require 'stringio'
+
+# Some parts adapted from
+# http://golang.org/src/pkg/json/decode.go and
+# http://golang.org/src/pkg/utf8/utf8.go
+module OkJson
+  extend self
+
+  class ParserError < ::StandardError; end
+
+  # Decodes a json document in string s and
+  # returns the corresponding ruby value.
+  # String s must be valid UTF-8. If you have
+  # a string in some other encoding, convert
+  # it first.
+  #
+  # String values in the resulting structure
+  # will be UTF-8.
+  def decode(s)
+    ts = lex(s)
+    v, ts = textparse(ts)
+    if ts.length > 0
+      raise OkJson::ParserError, 'trailing garbage'
+    end
+    v
+  end
+
+
+  # Parses a "json text" in the sense of RFC 4627.
+  # Returns the parsed value and any trailing tokens.
+  # Note: this is almost the same as valparse,
+  # except that it does not accept atomic values.
+  def textparse(ts)
+    if ts.length < 0
+      raise OkJson::ParserError, 'empty'
+    end
+
+    typ, _, val = ts[0]
+    case typ
+    when '{' then objparse(ts)
+    when '[' then arrparse(ts)
+    else valparse(ts)
+    end
+  end
+
+
+  # Parses a "value" in the sense of RFC 4627.
+  # Returns the parsed value and any trailing tokens.
+  def valparse(ts)
+    if ts.length < 0
+      raise OkJson::ParserError, 'empty'
+    end
+
+    typ, _, val = ts[0]
+    case typ
+    when '{' then objparse(ts)
+    when '[' then arrparse(ts)
+    when :val,:str then [val, ts[1..-1]]
+    else
+      raise OkJson::ParserError, "unexpected #{val.inspect}"
+    end
+  end
+
+
+  # Parses an "object" in the sense of RFC 4627.
+  # Returns the parsed value and any trailing tokens.
+  def objparse(ts)
+    ts = eat('{', ts)
+    obj = {}
+
+    if ts[0][0] == '}'
+      return obj, ts[1..-1]
+    end
+
+    k, v, ts = pairparse(ts)
+    obj[k] = v
+
+    if ts[0][0] == '}'
+      return obj, ts[1..-1]
+    end
+
+    loop do
+      ts = eat(',', ts)
+
+      k, v, ts = pairparse(ts)
+      obj[k] = v
+
+      if ts[0][0] == '}'
+        return obj, ts[1..-1]
+      end
+    end
+  end
+
+
+  # Parses a "member" in the sense of RFC 4627.
+  # Returns the parsed value and any trailing tokens.
+  def pairparse(ts)
+    (typ, _, k), ts = ts[0], ts[1..-1]
+    if typ != :str
+      raise OkJson::ParserError, "unexpected #{k.inspect}"
+    end
+    ts = eat(':', ts)
+    v, ts = valparse(ts)
+    [k, v, ts]
+  end
+
+
+  # Parses an "array" in the sense of RFC 4627.
+  # Returns the parsed value and any trailing tokens.
+  def arrparse(ts)
+    ts = eat('[', ts)
+    arr = []
+
+    if ts[0][0] == ']'
+      return arr, ts[1..-1]
+    end
+
+    v, ts = valparse(ts)
+    arr << v
+
+    if ts[0][0] == ']'
+      return arr, ts[1..-1]
+    end
+
+    loop do
+      ts = eat(',', ts)
+
+      v, ts = valparse(ts)
+      arr << v
+
+      if ts[0][0] == ']'
+        return arr, ts[1..-1]
+      end
+    end
+  end
+
+
+  def eat(typ, ts)
+    if ts[0][0] != typ
+      raise OkJson::ParserError, "expected #{typ} (got #{ts[0].inspect})"
+    end
+    ts[1..-1]
+  end
+
+
+  # Sans s and returns a list of json tokens,
+  # excluding white space (as defined in RFC 4627).
+  def lex(s)
+    ts = []
+    while s.length > 0
+      typ, lexeme, val = tok(s)
+      if typ == nil
+        raise OkJson::ParserError, "invalid character at #{s[0,10].inspect}"
+      end
+      if typ != :space
+        ts << [typ, lexeme, val]
+      end
+      s = s[lexeme.length..-1]
+    end
+    ts
+  end
+
+
+  # Scans the first token in s and
+  # returns a 3-element list, or nil
+  # if no such token exists.
+  #
+  # The first list element is one of
+  # '{', '}', ':', ',', '[', ']',
+  # :val, :str, and :space.
+  #
+  # The second element is the lexeme.
+  #
+  # The third element is the value of the
+  # token for :val and :str, otherwise
+  # it is the lexeme.
+  def tok(s)
+    case s[0]
+    when ?{  then ['{', s[0,1], s[0,1]]
+    when ?}  then ['}', s[0,1], s[0,1]]
+    when ?:  then [':', s[0,1], s[0,1]]
+    when ?,  then [',', s[0,1], s[0,1]]
+    when ?[  then ['[', s[0,1], s[0,1]]
+    when ?]  then [']', s[0,1], s[0,1]]
+    when ?n  then nulltok(s)
+    when ?t  then truetok(s)
+    when ?f  then falsetok(s)
+    when ?"  then strtok(s)
+    when Spc then [:space, s[0,1], s[0,1]]
+    when ?\t then [:space, s[0,1], s[0,1]]
+    when ?\n then [:space, s[0,1], s[0,1]]
+    when ?\r then [:space, s[0,1], s[0,1]]
+    else          numtok(s)
+    end
+  end
+
+
+  def nulltok(s);  s[0,4] == 'null'  && [:val, 'null',  nil]   end
+  def truetok(s);  s[0,4] == 'true'  && [:val, 'true',  true]  end
+  def falsetok(s); s[0,5] == 'false' && [:val, 'false', false] end
+
+
+  def numtok(s)
+    m = /-?([1-9][0-9]+|[0-9])([.][0-9]+)?([eE][+-]?[0-9]+)?/.match(s)
+    if m && m.begin(0) == 0
+      if m[3] && !m[2]
+        [:val, m[0], Integer(m[1])*(10**Integer(m[3][1..-1]))]
+      elsif m[2]
+        [:val, m[0], Float(m[0])]
+      else
+        [:val, m[0], Integer(m[0])]
+      end
+    end
+  end
+
+
+  def strtok(s)
+    m = /"([^"\\]|\\["\/\\bfnrt]|\\u[0-9a-fA-F]{4})*"/.match(s)
+    if ! m
+      raise OkJson::ParserError, "invalid string literal at #{abbrev(s)}"
+    end
+    [:str, m[0], unquote(m[0])]
+  end
+
+
+  def abbrev(s)
+    t = s[0,10]
+    p = t['`']
+    t = t[0,p] if p
+    t = t + '...' if t.length < s.length
+    '`' + t + '`'
+  end
+
+
+  # Converts a quoted json string literal q into a UTF-8-encoded string.
+  # The rules are different than for Ruby, so we cannot use eval.
+  # Unquote will raise OkJson::ParserError, an error if q contains control characters.
+  def unquote(q)
+    q = q[1...-1]
+    a = q.dup # allocate a big enough string
+    r, w = 0, 0
+    while r < q.length
+      c = q[r]
+      case true
+      when c == ?\\
+        r += 1
+        if r >= q.length
+          raise OkJson::ParserError, "string literal ends with a \"\\\": \"#{q}\""
+        end
+
+        case q[r]
+        when ?",?\\,?/,?'
+          a[w] = q[r]
+          r += 1
+          w += 1
+        when ?b,?f,?n,?r,?t
+          a[w] = Unesc[q[r]]
+          r += 1
+          w += 1
+        when ?u
+          r += 1
+          uchar = begin
+            hexdec4(q[r,4])
+          rescue RuntimeError => e
+            raise OkJson::ParserError, "invalid escape sequence \\u#{q[r,4]}: #{e}"
+          end
+          r += 4
+          if surrogate? uchar
+            if q.length >= r+6
+              uchar1 = hexdec4(q[r+2,4])
+              uchar = subst(uchar, uchar1)
+              if uchar != Ucharerr
+                # A valid pair; consume.
+                r += 6
+              end
+            end
+          end
+          w += ucharenc(a, w, uchar)
+        else
+          raise OkJson::ParserError, "invalid escape char #{q[r]} in \"#{q}\""
+        end
+      when c == ?", c < Spc
+        raise OkJson::ParserError, "invalid character in string literal \"#{q}\""
+      else
+        # Copy anything else byte-for-byte.
+        # Valid UTF-8 will remain valid UTF-8.
+        # Invalid UTF-8 will remain invalid UTF-8.
+        a[w] = c
+        r += 1
+        w += 1
+      end
+    end
+    a[0,w]
+  end
+
+
+  def hexdec4(s)
+    if s.length != 4
+      raise OkJson::ParserError, 'short'
+    end
+    (nibble(s[0])<<12) | (nibble(s[1])<<8) | (nibble(s[2])<<4) | nibble(s[3])
+  end
+
+
+  def subst(u1, u2)
+    if Usurr1 <= u1 && u1 < Usurr2 && Usurr2 <= u2 && u2 < Usurr3
+      return ((u1-Usurr1)<<10) | (u2-Usurr2) + Usurrself
+    end
+    return Ucharerr
+  end
+
+
+  def unsubst(u)
+    if u < Usurrself || u > Umax || surrogate?(u)
+      return Ucharerr, Ucharerr
+    end
+    u -= Usurrself
+    [Usurr1 + ((u>>10)&0x3ff), Usurr2 + (u&0x3ff)]
+  end
+
+
+  def surrogate?(u)
+    Usurr1 <= u && u < Usurr3
+  end
+
+
+  def nibble(c)
+    case true
+    when ?0 <= c && c <= ?9 then c.ord - ?0.ord
+    when ?a <= c && c <= ?z then c.ord - ?a.ord + 10
+    when ?A <= c && c <= ?Z then c.ord - ?A.ord + 10
+    else
+      raise OkJson::ParserError, "invalid hex code #{c}"
+    end
+  end
+
+
+  # Encodes x into a json text. It may contain only
+  # Array, Hash, String, Numeric, true, false, nil.
+  # (Note, this list excludes Symbol.)
+  # Strings contained in x must be valid UTF-8.
+  # Values that cannot be represented, such as
+  # Nan, Infinity, Symbol, and Proc, are encoded
+  # as null, in accordance with ECMA-262, 5th ed.
+  def encode(x)
+    case x
+    when Hash    then objenc(x)
+    when Array   then arrenc(x)
+    when String  then strenc(x)
+    when Numeric then numenc(x)
+    when Symbol  then strenc(x.to_s)
+    when true    then "true"
+    when false   then "false"
+    when nil     then "null"
+    else              "null"
+    end
+  end
+
+
+  def objenc(x)
+    '{' + x.map{|k,v| encode(k) + ':' + encode(v)}.join(',') + '}'
+  end
+
+
+  def arrenc(a)
+    '[' + a.map{|x| encode(x)}.join(',') + ']'
+  end
+
+
+  def strenc(s)
+    t = StringIO.new
+    t.putc(?")
+    r = 0
+    while r < s.length
+      case s[r]
+      when ?"  then t.print('\\"')
+      when ?\\ then t.print('\\\\')
+      when ?\b then t.print('\\b')
+      when ?\f then t.print('\\f')
+      when ?\n then t.print('\\n')
+      when ?\r then t.print('\\r')
+      when ?\t then t.print('\\t')
+      else
+        c = s[r]
+        case true
+        when Spc <= c && c <= ?~
+          t.putc(c)
+        when true
+          u, size = uchardec(s, r)
+          r += size - 1 # we add one more at the bottom of the loop
+          if u < 0x10000
+            t.print('\\u')
+            hexenc4(t, u)
+          else
+            u1, u2 = unsubst(u)
+            t.print('\\u')
+            hexenc4(t, u1)
+            t.print('\\u')
+            hexenc4(t, u2)
+          end
+        else
+          # invalid byte; skip it
+        end
+      end
+      r += 1
+    end
+    t.putc(?")
+    t.string
+  end
+
+
+  def hexenc4(t, u)
+    t.putc(Hex[(u>>12)&0xf])
+    t.putc(Hex[(u>>8)&0xf])
+    t.putc(Hex[(u>>4)&0xf])
+    t.putc(Hex[u&0xf])
+  end
+
+
+  def numenc(x)
+    if x.nan? || x.infinite?
+      return 'null'
+    end rescue nil
+    "#{x}"
+  end
+
+
+  # Decodes unicode character u from UTF-8
+  # bytes in string s at position i.
+  # Returns u and the number of bytes read.
+  def uchardec(s, i)
+    n = s.length - i
+    return [Ucharerr, 1] if n < 1
+
+    c0 = s[i].ord
+
+    # 1-byte, 7-bit sequence?
+    if c0 < Utagx
+      return [c0, 1]
+    end
+
+    # unexpected continuation byte?
+    return [Ucharerr, 1] if c0 < Utag2
+
+    # need continuation byte
+    return [Ucharerr, 1] if n < 2
+    c1 = s[i+1].ord
+    return [Ucharerr, 1] if c1 < Utagx || Utag2 <= c1
+
+    # 2-byte, 11-bit sequence?
+    if c0 < Utag3
+      u = (c0&Umask2)<<6 | (c1&Umaskx)
+      return [Ucharerr, 1] if u <= Uchar1max
+      return [u, 2]
+    end
+
+    # need second continuation byte
+    return [Ucharerr, 1] if n < 3
+    c2 = s[i+2].ord
+    return [Ucharerr, 1] if c2 < Utagx || Utag2 <= c2
+
+    # 3-byte, 16-bit sequence?
+    if c0 < Utag4
+      u = (c0&Umask3)<<12 | (c1&Umaskx)<<6 | (c2&Umaskx)
+      return [Ucharerr, 1] if u <= Uchar2max
+      return [u, 3]
+    end
+
+    # need third continuation byte
+    return [Ucharerr, 1] if n < 4
+    c3 = s[i+3].ord
+    return [Ucharerr, 1] if c3 < Utagx || Utag2 <= c3
+
+    # 4-byte, 21-bit sequence?
+    if c0 < Utag5
+      u = (c0&Umask4)<<18 | (c1&Umaskx)<<12 | (c2&Umaskx)<<6 | (c3&Umaskx)
+      return [Ucharerr, 1] if u <= Uchar3max
+      return [u, 4]
+    end
+
+    return [Ucharerr, 1]
+  end
+
+
+  # Encodes unicode character u as UTF-8
+  # bytes in string a at position i.
+  # Returns the number of bytes written.
+  def ucharenc(a, i, u)
+    case true
+    when u <= Uchar1max
+      a[i] = (u & 0xff).chr
+      1
+    when u <= Uchar2max
+      a[i+0] = (Utag2 | ((u>>6)&0xff)).chr
+      a[i+1] = (Utagx | (u&Umaskx)).chr
+      2
+    when u <= Uchar3max
+      a[i+0] = (Utag3 | ((u>>12)&0xff)).chr
+      a[i+1] = (Utagx | ((u>>6)&Umaskx)).chr
+      a[i+2] = (Utagx | (u&Umaskx)).chr
+      3
+    else
+      a[i+0] = (Utag4 | ((u>>18)&0xff)).chr
+      a[i+1] = (Utagx | ((u>>12)&Umaskx)).chr
+      a[i+2] = (Utagx | ((u>>6)&Umaskx)).chr
+      a[i+3] = (Utagx | (u&Umaskx)).chr
+      4
+    end
+  end
+
+  Utagx = 0x80 # 1000 0000
+  Utag2 = 0xc0 # 1100 0000
+  Utag3 = 0xe0 # 1110 0000
+  Utag4 = 0xf0 # 1111 0000
+  Utag5 = 0xF8 # 1111 1000
+  Umaskx = 0x3f # 0011 1111
+  Umask2 = 0x1f # 0001 1111
+  Umask3 = 0x0f # 0000 1111
+  Umask4 = 0x07 # 0000 0111
+  Uchar1max = (1<<7) - 1
+  Uchar2max = (1<<11) - 1
+  Uchar3max = (1<<16) - 1
+  Ucharerr = 0xFFFD # unicode "replacement char"
+  Usurrself = 0x10000
+  Usurr1 = 0xd800
+  Usurr2 = 0xdc00
+  Usurr3 = 0xe000
+  Umax = 0x10ffff
+
+  Spc = ' '[0]
+  Unesc = {?b=>?\b, ?f=>?\f, ?n=>?\n, ?r=>?\r, ?t=>?\t}
+  Hex = '0123456789abcdef'
+end