multipart_parser 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 1b5401a95c9f84dd50f880f1b3f7600f75ef67c7
-  data.tar.gz: 7dd6495855fe2ffb3352683f382871ea2e7e3d7c
+  metadata.gz: dc18a37bf3a19151afcd3124b1cd17a3aea71da5
+  data.tar.gz: bfa0342a40514e68f5e8550ca3ad5f92b84dfe1c
 SHA512:
-  metadata.gz: 6ade21353b43a28ddbeb6c75ea07970070dfbe79692b2977ea438236f26ff43fd58d7ca6b1fca91c2e0394a4d0510931e8b5253e2b53922624db5bbeae076ed7
-  data.tar.gz: b19416e99743307d1696b7bf792c08c31416e9548b9cd14e5f67eba29fbd5282aae371a57de340f6f88eeeb00e5f73e74e3817b73510d53a2a469433b8cb31eb
+  metadata.gz: 47060a489239ef727a32472ff2930d7ed227ce8ecdb437cdc09cdeaa430a0e6f525b2cfa91dc62ed8da0423d18bcff8d9715284e8d8f5b960c6ef22913ebd15c
+  data.tar.gz: 5c4934e4d5d787349c2d6ff8030923f0cf32d7fa9ffa06a0416b3c8fd2a1bfae89dd6c32095fef8e479c9d1dcde2ba7eaa4e79d5c31426dfa32da552becc6c73

data/ext/multipart_parser/multipart_parser_c.c

@@ -50,6 +50,8 @@ enum state {
   s_uninitialized = 1,
   s_start,
   s_start_boundary,
+  s_preamble,
+  s_preamble_almost_boundary,
   s_header_field_start,
   s_header_field,
   s_headers_almost_done,
@@ -137,12 +139,37 @@ size_t multipart_parser_c_execute(multipart_parser_c* p, const multipart_parser_
           p->state = s_header_field_start;
           break;
         }
+
+        /* if starting boundaru doesn't match, assume we are reading the preamble */
         if (c != p->multipart_boundary[p->index]) {
-          return i;
+          p->index = 0;
+
+          if (c == CR) { /* smallest preable is CR LF */
+
+            p->state = s_preamble_almost_boundary;
+          } else {
+            p->state = s_preamble;
+          }
+          break;
         }
+
         p->index++;
         break;
 
+      case s_preamble:
+        if (c == CR) {
+            p->state = s_preamble_almost_boundary;
+        }
+        break;
+
+      case s_preamble_almost_boundary:
+        if(c == LF) {
+          p->state = s_start_boundary;
+        } else {
+          p->state = s_preamble;
+        }
+        break;
+
       case s_header_field_start:
         multipart_log("s_header_field_start");
         mark = i;

data/lib/multipart_parser/version.rb

@@ -1,3 +1,3 @@
 class MultipartParser
-  VERSION = "0.0.1"
+  VERSION = "0.0.2"
 end

data/spec/multipart_parser_spec.rb

@@ -151,7 +151,113 @@ describe MultipartParser do
     expect(MultipartParser::VERSION).not_to be nil
   end
 
+
   specify { expect { MultipartParser.new }.to raise_error(ArgumentError) }
 
+  context "multipart_parser.c" do
+    let(:parser) { MultipartParser.new "Boundary+17376C87E2579930" }
+
+
+    # https://www.ietf.org/rfc/rfc2046.txt
+
+    #   boundary := 0*69<bchars> bcharsnospace
+
+    #   bchars := bcharsnospace / " "
+
+    #   bcharsnospace := DIGIT / ALPHA / "'" / "(" / ")" /
+    #                    "+" / "_" / "," / "-" / "." /
+    #                    "/" / ":" / "=" / "?"
+
+    # Overall, the body of a "multipart" entity may be specified as
+    # follows:
+
+    #   dash-boundary := "--" boundary
+    #                    ; boundary taken from the value of
+    #                    ; boundary parameter of the
+    #                    ; Content-Type field.
+
+    #   multipart-body := [preamble CRLF]
+    #                     dash-boundary transport-padding CRLF
+    #                     body-part *encapsulation
+    #                     close-delimiter transport-padding
+    #                     [CRLF epilogue]
+
+
+    #   transport-padding := *LWSP-char
+    #                        ; Composers MUST NOT generate
+    #                        ; non-zero length transport
+    #                        ; padding, but receivers MUST
+    #                        ; be able to handle padding
+    #                        ; added by message transports.
+
+    #   encapsulation := delimiter transport-padding
+    #                    CRLF body-part
+
+    #   delimiter := CRLF dash-boundary
+
+    #   close-delimiter := delimiter "--"
+
+    #   preamble := discard-text
+
+    #   epilogue := discard-text
+
+    #   discard-text := *(*text CRLF) *text
+    #                   ; May be ignored or discarded.
+
+    #   body-part := MIME-part-headers [CRLF *OCTET]
+    #                ; Lines in a body-part must not start
+    #                ; with the specified dash-boundary and
+    #                ; the delimiter must not appear anywhere
+    #                ; in the body part.  Note that the
+    #                ; semantics of a body-part differ from
+    #                ; the semantics of a message, as
+    #                ; described in the text.
+
+    #   OCTET := <any 0-255 octet value>
+
+    it "allows a preamble" do
+      #https://www.ietf.org/rfc/rfc2046.txt  section 5.1.1
+
+      #    There appears to be room for additional information prior to the
+      # first boundary delimiter line and following the final boundary
+      # delimiter line.  These areas should generally be left blank, and
+      # IMPLEMENTATIONS MUST IGNORE ANYTHING THAT APPEARS BEFORE THE FIRST
+      # BOUNDARY DELIMITER LINE OR AFTER THE LAST ONE.
+
+      parser.on_data = handler
+
+      expect(handler).to receive(:call).with("first frame")
+
+      parser << "preamble\r\n--Boundary+17376C87E2579930\r\n\r\nfirst frame\r\n";
+      parser << "--Boundary+17376C87E2579930--\r\n"
+
+    end
+
+    it "requires the preamble to be terminated with a CRLF" do
+
+      #   multipart-body := [preamble CRLF]
+      #                     dash-boundary transport-padding CRLF
+
+      parser.on_data = handler
+
+      expect(handler).to_not receive(:call)
+
+      parser << "preamble--Boundary+17376C87E2579930\r\n\r\nfirst frame\r\n";
+      parser << "--Boundary+17376C87E2579930--\r\n"
+
+    end
+
+    it "handles a preamble that is only CRLF" do
+
+      parser.on_data = handler
+
+      expect(handler).to receive(:call).with("first frame")
+
+      parser << "\r\n--Boundary+17376C87E2579930\r\n\r\nfirst frame\r\n";
+      parser << "--Boundary+17376C87E2579930--\r\n"
+
+    end
+  end
+
 end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: multipart_parser
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Benjamin Bryant
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-08-09 00:00:00.000000000 Z
+date: 2015-08-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler