--- a/mercurial/verify.py Wed Mar 29 22:26:16 2017 +0200
+++ b/mercurial/verify.py Wed Mar 29 14:45:01 2017 -0700
@@ -379,7 +379,53 @@
else:
del filenodes[f][n]
- # verify contents
+ # Verify contents. 4 cases to care about:
+ #
+ # common: the most common case
+ # rename: with a rename
+ # meta: file content starts with b'\1\n', the metadata
+ # header defined in filelog.py, but without a rename
+ # ext: content stored externally
+ #
+ # More formally, their differences are shown below:
+ #
+ # | common | rename | meta | ext
+ # -------------------------------------------------------
+ # flags() | 0 | 0 | 0 | not 0
+ # renamed() | False | True | False | ?
+ # rawtext[0:2]=='\1\n'| False | True | True | ?
+ #
+ # "rawtext" means the raw text stored in revlog data, which
+ # could be retrieved by "revision(rev, raw=True)". "text"
+ # mentioned below is "revision(rev, raw=False)".
+ #
+ # There are 3 different lengths stored physically:
+ # 1. L1: rawsize, stored in revlog index
+ # 2. L2: len(rawtext), stored in revlog data
+ # 3. L3: len(text), stored in revlog data if flags==0, or
+ # possibly somewhere else if flags!=0
+ #
+ # L1 should be equal to L2. L3 could be different from them.
+ # "text" may or may not affect commit hash depending on flag
+ # processors (see revlog.addflagprocessor).
+ #
+ # | common | rename | meta | ext
+ # -------------------------------------------------
+ # rawsize() | L1 | L1 | L1 | L1
+ # size() | L1 | L2-LM | L1(*) | L1 (?)
+ # len(rawtext) | L2 | L2 | L2 | L2
+ # len(text) | L2 | L2 | L2 | L3
+ # len(read()) | L2 | L2-LM | L2-LM | L3 (?)
+ #
+ # LM: length of metadata, depending on rawtext
+ # (*): not ideal, see comment in filelog.size
+ # (?): could be "- len(meta)" if the resolved content has
+ # rename metadata
+ #
+ # Checks needed to be done:
+ # 1. length check: L1 == L2, in all cases.
+ # 2. hash check: depending on flag processor, we may need to
+ # use either "text" (external), or "rawtext" (in revlog).
try:
l = len(fl.read(n))
rp = fl.renamed(n)