| … | |
… | |
| 679 | |
679 | |
| 680 | JSON::XS->new->decode_prefix ("[1] the tail") |
680 | JSON::XS->new->decode_prefix ("[1] the tail") |
| 681 | => ([], 3) |
681 | => ([], 3) |
| 682 | |
682 | |
| 683 | =back |
683 | =back |
|
|
684 | |
|
|
685 | |
|
|
686 | =head1 INCREMENTAL PARSING |
|
|
687 | |
|
|
688 | [This section is still EXPERIMENTAL] |
|
|
689 | |
|
|
690 | In some cases, there is the need for incremental parsing of JSON |
|
|
691 | texts. While this module always has to keep both JSON text and resulting |
|
|
692 | Perl data structure in memory at one time, it does allow you to parse a |
|
|
693 | JSON stream incrementally. It does so by accumulating text until it has |
|
|
694 | a full JSON object, which it then can decode. This process is similar to |
|
|
695 | using C<decode_prefix> to see if a full JSON object is available, but is |
|
|
696 | much more efficient (JSON::XS will only attempt to parse the JSON text |
|
|
697 | once it is sure it has enough text to get a decisive result, using a very |
|
|
698 | simple but truly incremental parser). |
|
|
699 | |
|
|
700 | The following two methods deal with this. |
|
|
701 | |
|
|
702 | =over 4 |
|
|
703 | |
|
|
704 | =item [void, scalar or list context] = $json->incr_parse ([$string]) |
|
|
705 | |
|
|
706 | This is the central parsing function. It can both append new text and |
|
|
707 | extract objects from the stream accumulated so far (both of these |
|
|
708 | functions are optional). |
|
|
709 | |
|
|
710 | If C<$string> is given, then this string is appended to the already |
|
|
711 | existing JSON fragment stored in the C<$json> object. |
|
|
712 | |
|
|
713 | After that, if the function is called in void context, it will simply |
|
|
714 | return without doing anything further. This can be used to add more text |
|
|
715 | in as many chunks as you want. |
|
|
716 | |
|
|
717 | If the method is called in scalar context, then it will try to extract |
|
|
718 | exactly I<one> JSON object. If that is successful, it will return this |
|
|
719 | object, otherwise it will return C<undef>. This is the most common way of |
|
|
720 | using the method. |
|
|
721 | |
|
|
722 | And finally, in list context, it will try to extract as many objects |
|
|
723 | from the stream as it can find and return them, or the empty list |
|
|
724 | otherwise. For this to work, there must be no separators between the JSON |
|
|
725 | objects or arrays, instead they must be concatenated back-to-back. |
|
|
726 | |
|
|
727 | =item $lvalue_string = $json->incr_text |
|
|
728 | |
|
|
729 | This method returns the currently stored JSON fragment as an lvalue, that |
|
|
730 | is, you can manipulate it. This I<only> works when a preceding call to |
|
|
731 | C<incr_parse> in I<scalar context> successfully returned an object. Under |
|
|
732 | all other circumstances you must not call this function (I mean it. |
|
|
733 | although in simple tests it might actually work, it I<will> fail under |
|
|
734 | real world conditions). As a special exception, you can also call this |
|
|
735 | method before having parsed anything. |
|
|
736 | |
|
|
737 | This function is useful in two cases: a) finding the trailing text after a |
|
|
738 | JSON object or b) parsing multiple JSON objects separated by non-JSON text |
|
|
739 | (such as commas). |
|
|
740 | |
|
|
741 | =back |
|
|
742 | |
|
|
743 | =head2 LIMITATIONS |
|
|
744 | |
|
|
745 | All options that affect decoding are supported, except |
|
|
746 | C<allow_nonref>. The reason for this is that it cannot be made to |
|
|
747 | work sensibly: JSON objects and arrays are self-delimited, i.e. you can concatenate |
|
|
748 | them back to back and still decode them perfectly. This does not hold true |
|
|
749 | for JSON numbers, however. |
|
|
750 | |
|
|
751 | For example, is the string C<1> a single JSON number, or is it simply the |
|
|
752 | start of C<12>? Or is C<12> a single JSON number, or the concatenation |
|
|
753 | of C<1> and C<2>? In neither case you can tell, and this is why JSON::XS |
|
|
754 | takes the conservative route and disallows this case. |
|
|
755 | |
|
|
756 | =head2 EXAMPLES |
|
|
757 | |
|
|
758 | Some examples will make all this clearer. First, a simple example that |
|
|
759 | works similarly to C<decode_prefix>: We want to decode the JSON object at |
|
|
760 | the start of a string and identify the portion after the JSON object: |
|
|
761 | |
|
|
762 | my $text = "[1,2,3] hello"; |
|
|
763 | |
|
|
764 | my $json = new JSON::XS; |
|
|
765 | |
|
|
766 | my $obj = $json->incr_parse ($text) |
|
|
767 | or die "expected JSON object or array at beginning of string"; |
|
|
768 | |
|
|
769 | my $tail = $json->incr_text; |
|
|
770 | # $tail now contains " hello" |
|
|
771 | |
|
|
772 | Easy, isn't it? |
|
|
773 | |
|
|
774 | Now for a more complicated example: Imagine a hypothetical protocol where |
|
|
775 | you read some requests from a TCP stream, and each request is a JSON |
|
|
776 | array, without any separation between them (in fact, it is often useful to |
|
|
777 | use newlines as "separators", as these get interpreted as whitespace at |
|
|
778 | the start of the JSON text, which makes it possible to test said protocol |
|
|
779 | with C<telnet>...). |
|
|
780 | |
|
|
781 | Here is how you'd do it (it is trivial to write this in an event-based |
|
|
782 | manner): |
|
|
783 | |
|
|
784 | my $json = new JSON::XS; |
|
|
785 | |
|
|
786 | # read some data from the socket |
|
|
787 | while (sysread $socket, my $buf, 4096) { |
|
|
788 | |
|
|
789 | # split and decode as many requests as possible |
|
|
790 | for my $request ($json->incr_parse ($buf)) { |
|
|
791 | # act on the $request |
|
|
792 | } |
|
|
793 | } |
|
|
794 | |
|
|
795 | Another complicated example: Assume you have a string with JSON objects |
|
|
796 | or arrays, all separated by (optional) comma characters (e.g. C<[1],[2], |
|
|
797 | [3]>). To parse them, we have to skip the commas between the JSON texts, |
|
|
798 | and here is where the lvalue-ness of C<incr_text> comes in useful: |
|
|
799 | |
|
|
800 | my $text = "[1],[2], [3]"; |
|
|
801 | my $json = new JSON::XS; |
|
|
802 | |
|
|
803 | # void context, so no parsing done |
|
|
804 | $json->incr_parse ($text); |
|
|
805 | |
|
|
806 | # now extract as many objects as possible. note the |
|
|
807 | # use of scalar context so incr_text can be called. |
|
|
808 | while (my $obj = $json->incr_parse) { |
|
|
809 | # do something with $obj |
|
|
810 | |
|
|
811 | # now skip the optional comma |
|
|
812 | $json->incr_text =~ s/^ \s* , //x; |
|
|
813 | } |
|
|
814 | |
|
|
815 | Now lets go for a very complex example: Assume that you have a gigantic |
|
|
816 | JSON array-of-objects, many gigabytes in size, and you want to parse it, |
|
|
817 | but you cannot load it into memory fully (this has actually happened in |
|
|
818 | the real world :). |
|
|
819 | |
|
|
820 | Well, you lost, you have to implement your own JSON parser. But JSON::XS |
|
|
821 | can still help you: You implement a (very simple) array parser and let |
|
|
822 | JSON decode the array elements, which are all full JSON objects on their |
|
|
823 | own (this wouldn't work if the array elements could be JSON numbers, for |
|
|
824 | example): |
|
|
825 | |
|
|
826 | my $json = new JSON::XS; |
|
|
827 | |
|
|
828 | # open the monster |
|
|
829 | open my $fh, "<bigfile.json" |
|
|
830 | or die "bigfile: $!"; |
|
|
831 | |
|
|
832 | # first parse the initial "[" |
|
|
833 | for (;;) { |
|
|
834 | sysread $fh, my $buf, 65536 |
|
|
835 | or die "read error: $!"; |
|
|
836 | $json->incr_parse ($buf); # void context, so no parsing |
|
|
837 | |
|
|
838 | # Exit the loop once we found and removed(!) the initial "[". |
|
|
839 | # In essence, we are (ab-)using the $json object as a simple scalar |
|
|
840 | # we append data to. |
|
|
841 | last if $json->incr_text =~ s/^ \s* \[ //x; |
|
|
842 | } |
|
|
843 | |
|
|
844 | # now we have the skipped the initial "[", so continue |
|
|
845 | # parsing all the elements. |
|
|
846 | for (;;) { |
|
|
847 | # in this loop we read data until we got a single JSON object |
|
|
848 | for (;;) { |
|
|
849 | if (my $obj = $json->incr_parse) { |
|
|
850 | # do something with $obj |
|
|
851 | last; |
|
|
852 | } |
|
|
853 | |
|
|
854 | # add more data |
|
|
855 | sysread $fh, my $buf, 65536 |
|
|
856 | or die "read error: $!"; |
|
|
857 | $json->incr_parse ($buf); # void context, so no parsing |
|
|
858 | } |
|
|
859 | |
|
|
860 | # in this loop we read data until we either found and parsed the |
|
|
861 | # separating "," between elements, or the final "]" |
|
|
862 | for (;;) { |
|
|
863 | # first skip whitespace |
|
|
864 | $json->incr_text =~ s/^\s*//; |
|
|
865 | |
|
|
866 | # if we find "]", we are done |
|
|
867 | if ($json->incr_text =~ s/^\]//) { |
|
|
868 | print "finished.\n"; |
|
|
869 | exit; |
|
|
870 | } |
|
|
871 | |
|
|
872 | # if we find ",", we can continue with the next element |
|
|
873 | if ($json->incr_text =~ s/^,//) { |
|
|
874 | last; |
|
|
875 | } |
|
|
876 | |
|
|
877 | # if we find anything else, we have a parse error! |
|
|
878 | if (length $json->incr_text) { |
|
|
879 | die "parse error near ", $json->incr_text; |
|
|
880 | } |
|
|
881 | |
|
|
882 | # else add more data |
|
|
883 | sysread $fh, my $buf, 65536 |
|
|
884 | or die "read error: $!"; |
|
|
885 | $json->incr_parse ($buf); # void context, so no parsing |
|
|
886 | } |
|
|
887 | |
|
|
888 | This is a complex example, but most of the complexity comes from the fact |
|
|
889 | that we are trying to be correct (bear with me if I am wrong, I never ran |
|
|
890 | the above example :). |
|
|
891 | |
| 684 | |
892 | |
| 685 | |
893 | |
| 686 | =head1 MAPPING |
894 | =head1 MAPPING |
| 687 | |
895 | |
| 688 | This section describes how JSON::XS maps Perl values to JSON values and |
896 | This section describes how JSON::XS maps Perl values to JSON values and |
