split_for_sort: Split a given file into buckets

The target bucket is decided based on the first X characters of a line.
The bucket name gets a prefix defined as argument and can be sorted
faster on weak hardware. Note: This is just a split alternative.

Real world usage in a shell script with a file in which the first 10
characters are the equal in each line, the following 2 bytes are
evaluated for splitting:

split_for_sort TMPSFS 12 raw_data.txt
for f in TMPSFS ; do
    sort -o "${f}_sorted" -u "${f}"
done
\# Rely on the argument resolution to go with lexical order
cat TMPSFS*_sorted > sorted_data.txt
rm TMPSFS*

1 files changed, 35 insertions, 0 deletions

diff --git a/Makefile b/Makefile
new file mode 100644
index 0000000..4d8a55d
--- /dev/null
+++ b/Makefile
@@ -0,0 +1,35 @@
+
+
+CFLAGS += -Wall -Wextra -Wformat -Wformat=2 -Wconversion -Wimplicit-fallthrough -Werror=format-security \
+	-Wbidi-chars=any -Werror=implicit -Werror=incompatible-pointer-types -Werror=int-conversion \
+	-fno-delete-null-pointer-checks -fstack-clash-protection -fstack-protector-strong -fstrict-flex-arrays=3
+
+DEBUG_CFLAGS = -DDEBUGBUILD -g -Werror -fsanitize=address
+
+PROD_CFLAGS = -O2 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=3 -FPIE -pie -Wl,-z,noexecstack -Wl,--as-needed -Wl,--no-copy-dt-needed-entries
+
+CFLAGS += -I include
+
+all: out/split_for_sort
+
+
+
+clean: out
+	rm -fv out/debug/*
+	rm -fv out/*
+	rm -rfv out
+
+out:
+	mkdir out
+
+out/debug: out
+	mkdir out/debug
+
+# Lazy, not splitting compiler & linker calls
+out/split_for_sort: out src/split_for_sort.c include/output.h
+	${CC} -o $@ ${CFLAGS} ${PROD_CFLAGS} src/split_for_sort.c
+
+out/debug/split_for_sort_debug: out/debug src/split_for_sort.c include/output.h
+	${CC} -o $@ ${CFLAGS} ${DEBUG_CFLAGS} src/split_for_sort.c
+
+