aboutsummaryrefslogtreecommitdiffstats
path: root/lib
diff options
context:
space:
mode:
authorHans Bolinder <[email protected]>2017-10-23 14:47:36 +0200
committerGitHub <[email protected]>2017-10-23 14:47:36 +0200
commit9bbe5884cf620aa1c70b92b6e0f3a9d5c3866a9c (patch)
tree832da2f0517faac7abf909851dfc857ef80f6495 /lib
parent38dcead7d9736d0c5495e36ad04a1ff14607e1c3 (diff)
parentd14f1512b01261c1cfdff2effe587118d9ddc012 (diff)
downloadotp-9bbe5884cf620aa1c70b92b6e0f3a9d5c3866a9c.tar.gz
otp-9bbe5884cf620aa1c70b92b6e0f3a9d5c3866a9c.tar.bz2
otp-9bbe5884cf620aa1c70b92b6e0f3a9d5c3866a9c.zip
Merge pull request #1565 from mikpe/stdlib-base64-decode-speedup
base64:decode(List) optimized reimplementation OTP-14624
Diffstat (limited to 'lib')
-rw-r--r--lib/stdlib/src/base64.erl108
1 files changed, 72 insertions, 36 deletions
diff --git a/lib/stdlib/src/base64.erl b/lib/stdlib/src/base64.erl
index 5885745fb1..c8cf6fdffe 100644
--- a/lib/stdlib/src/base64.erl
+++ b/lib/stdlib/src/base64.erl
@@ -113,9 +113,9 @@ encode_binary(Bin) ->
Data :: ascii_binary().
decode(Bin) when is_binary(Bin) ->
- decode_binary(<<>>, Bin);
+ decode_binary(Bin, <<>>);
decode(List) when is_list(List) ->
- list_to_binary(decode_l(List)).
+ decode_list(List, <<>>).
-spec mime_decode(Base64) -> Data when
Base64 :: ascii_string() | ascii_binary(),
@@ -186,31 +186,41 @@ mime_decode_to_string(List) when is_list(List) ->
bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,
bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,bad,bad}).
-decode_binary(Result0, <<C:8,T0/bits>>) ->
- case element(C, ?DECODE_MAP) of
- bad ->
- erlang:error({badarg,C});
- ws ->
- decode_binary(Result0, T0);
- eq ->
- case strip_ws(T0) of
- <<$=:8,T/binary>> ->
- <<>> = strip_ws(T),
- Split = byte_size(Result0) - 1,
- <<Result:Split/bytes,_:4>> = Result0,
- Result;
- T ->
- <<>> = strip_ws(T),
- Split = byte_size(Result0) - 1,
- <<Result:Split/bytes,_:2>> = Result0,
- Result
- end;
- Bits ->
- decode_binary(<<Result0/bits,Bits:6>>, T0)
+decode_binary(<<C1:8, Cs/bits>>, A) ->
+ case element(C1, ?DECODE_MAP) of
+ ws -> decode_binary(Cs, A);
+ B1 -> decode_binary(Cs, A, B1)
end;
-decode_binary(Result, <<>>) ->
- true = is_binary(Result),
- Result.
+decode_binary(<<>>, A) ->
+ A.
+
+decode_binary(<<C2:8, Cs/bits>>, A, B1) ->
+ case element(C2, ?DECODE_MAP) of
+ ws -> decode_binary(Cs, A, B1);
+ B2 -> decode_binary(Cs, A, B1, B2)
+ end.
+
+decode_binary(<<C3:8, Cs/bits>>, A, B1, B2) ->
+ case element(C3, ?DECODE_MAP) of
+ ws -> decode_binary(Cs, A, B1, B2);
+ B3 -> decode_binary(Cs, A, B1, B2, B3)
+ end.
+
+decode_binary(<<C4:8, Cs/bits>>, A, B1, B2, B3) ->
+ case element(C4, ?DECODE_MAP) of
+ ws -> decode_binary(Cs, A, B1, B2, B3);
+ eq when B3 =:= eq -> only_ws_binary(Cs, <<A/binary,B1:6,(B2 bsr 4):2>>);
+ eq -> only_ws_binary(Cs, <<A/binary,B1:6,B2:6,(B3 bsr 2):4>>);
+ B4 -> decode_binary(Cs, <<A/binary,B1:6,B2:6,B3:6,B4:6>>)
+ end.
+
+only_ws_binary(<<>>, A) ->
+ A;
+only_ws_binary(<<C:8, Cs/bits>>, A) ->
+ case element(C, ?DECODE_MAP) of
+ ws -> only_ws_binary(Cs, A);
+ _ -> erlang:error(function_clause)
+ end.
%% Skipping pad character if not at end of string. Also liberal about
%% excess padding and skipping of other illegal (non-base64 alphabet)
@@ -262,6 +272,42 @@ mime_decode_binary_after_eq(Result0, <<>>, Eq) ->
Result
end.
+decode_list([C1 | Cs], A) ->
+ case element(C1, ?DECODE_MAP) of
+ ws -> decode_list(Cs, A);
+ B1 -> decode_list(Cs, A, B1)
+ end;
+decode_list([], A) ->
+ A.
+
+decode_list([C2 | Cs], A, B1) ->
+ case element(C2, ?DECODE_MAP) of
+ ws -> decode_list(Cs, A, B1);
+ B2 -> decode_list(Cs, A, B1, B2)
+ end.
+
+decode_list([C3 | Cs], A, B1, B2) ->
+ case element(C3, ?DECODE_MAP) of
+ ws -> decode_list(Cs, A, B1, B2);
+ B3 -> decode_list(Cs, A, B1, B2, B3)
+ end.
+
+decode_list([C4 | Cs], A, B1, B2, B3) ->
+ case element(C4, ?DECODE_MAP) of
+ ws -> decode_list(Cs, A, B1, B2, B3);
+ eq when B3 =:= eq -> only_ws(Cs, <<A/binary,B1:6,(B2 bsr 4):2>>);
+ eq -> only_ws(Cs, <<A/binary,B1:6,B2:6,(B3 bsr 2):4>>);
+ B4 -> decode_list(Cs, <<A/binary,B1:6,B2:6,B3:6,B4:6>>)
+ end.
+
+only_ws([], A) ->
+ A;
+only_ws([C | Cs], A) ->
+ case element(C, ?DECODE_MAP) of
+ ws -> only_ws(Cs, A);
+ _ -> erlang:error(function_clause)
+ end.
+
decode([], A) -> A;
decode([$=,$=,C2,C1|Cs], A) ->
Bits2x6 = (b64d(C1) bsl 18) bor (b64d(C2) bsl 12),
@@ -292,16 +338,6 @@ strip_spaces([$\r|Cs], A) -> strip_spaces(Cs, A);
strip_spaces([$\n|Cs], A) -> strip_spaces(Cs, A);
strip_spaces([C|Cs], A) -> strip_spaces(Cs, [C | A]).
-strip_ws(<<$\t,T/binary>>) ->
- strip_ws(T);
-strip_ws(<<$\n,T/binary>>) ->
- strip_ws(T);
-strip_ws(<<$\r,T/binary>>) ->
- strip_ws(T);
-strip_ws(<<$\s,T/binary>>) ->
- strip_ws(T);
-strip_ws(T) -> T.
-
%% Skipping pad character if not at end of string. Also liberal about
%% excess padding and skipping of other illegal (non-base64 alphabet)
%% characters. See section 3.3 of RFC4648