libutil: rewrite RewritingSink as source

the rewriting sink was just broken. when given a rewrite set that
contained a key that is also a proper infix of another key it was
possible to produce an incorrectly rewritten result if the writer
used the wrong block size. fixing this duplicates rewriteStrings,
to avoid this we'll rewrite rewriteStrings to use RewritingSource
in a new mode that'll allow rewrites we had previously forbidden.

Change-Id: I57fa0a9a994e654e11d07172b8e31d15f0b7e8c0

1 files changed, 13 insertions, 8 deletions

diff --git a/src/libutil/references.hh b/src/libutil/references.hh
index 3fefd824b..f0f467190 100644
--- a/src/libutil/references.hh
+++ b/src/libutil/references.hh
@@ -23,19 +23,24 @@ public:
     void operator () (std::string_view data) override;
 };
 
-struct RewritingSink : Sink
+struct RewritingSource : Source
 {
+    const std::string::size_type maxRewriteSize;
+    const std::string initials;
     const StringMap rewrites;
-    std::string::size_type maxRewriteSize;
-    std::string prev;
-    Sink & nextSink;
+    std::string rewritten, buffered;
+    std::string_view unreturned;
+    Source * inner;
 
-    RewritingSink(const std::string & from, const std::string & to, Sink & nextSink);
-    RewritingSink(const StringMap & rewrites, Sink & nextSink);
+    static constexpr struct may_change_size_t {
+        explicit may_change_size_t() = default;
+    } may_change_size{};
 
-    void operator () (std::string_view data) override;
+    RewritingSource(const std::string & from, const std::string & to, Source & inner);
+    RewritingSource(StringMap rewrites, Source & inner);
+    RewritingSource(may_change_size_t, StringMap rewrites, Source & inner);
 
-    void flush();
+    size_t read(char * data, size_t len) override;
 };
 
 HashResult computeHashModulo(HashType ht, const std::string & modulus, Source & source);