mirror of https://github.com/citusdata/citus.git
a53fb90ef9
I came across several places we weren't as flexible or resilient as we should have been in our build logic. They include: * Not using `DESTDIR` in the install-header destination * Allowing callers to specify `VPATH` or `srcdir` (which breaks) * Using absolute path for SCRIPTS (9.5 prepends srcdir) * Including libpq-int in a confusing way (extracted this function) * Having server includes come first during csql build (client must) In particular, I hit all of these attempting to build with pg_buildext in Debian. It passes in an explicit VPATH, as well as srcdir (breaking all recursive make invocations), and also uses DESTDIR during install. In addition, a PGDG-enabled Debian box will have the latest libpq-dev headers (e.g. 9.5) even when building against an older server version (e.g. 9.4). This leads to problems when including e.g. `c.h`, which is ambiguous. While compiling more client-side code (csql), we need to ensure the newer libpq headers are included _first_, so I fixed that. |
||
|---|---|---|
| .. | ||
| backend | ||
| bin | ||
| include | ||
| test/regress | ||