wc

commit b9025a01db609ca07fdb0a0b8b10c6404f2d20ff
parent 727a6f6485e014bdd810c73e00329ff2a6a6ff51
Author: NunoSempere <nuno.sempere@protonmail.com>
Date:   Sat,  9 Sep 2023 00:02:31 +0200

add usage, start looking into gnu utils

Diffstat:
M
README.md
 | 
8
+++++---
M
makefile
 | 
13
+++++++------
M
wc
 | 
0

M
wc.c
 | 
20
+++++++++++++-------

4 files changed, 25 insertions(+), 16 deletions(-)
diff --git a/README.md b/README.md
@@ -11,9 +11,11 @@ Desiderata
 
 Steps:
 
-- [ ] Look into how C utilities both read from stdin and from files.
-- [ ] ...
+- [x] Look into how C utilities both read from stdin and from files.
+- [x] Program first version of the utility
 - [ ] Compare with other implementations, see how they do it, after I've read my own version
-  - Compare with gnu utils, 
+  - [ ] Compare with gnu utils, 
   - Compare with musl/busybox implementations, 
   - Maybe make some pull requests, if I'm doing something better?
+- [ ] Install to ww, but check that ww is empty (installing to wc2 or smth would mean that you don't save that many keypresses vs wc -w)
+- [ ] ...
diff --git a/makefile b/makefile
@@ -9,7 +9,7 @@ CC=gcc
 
 # Main file
 SRC=wc.c
-OUTPUT=wc
+OUT=wc
 
 ## Flags
 DEBUG= #'-g'
@@ -24,13 +24,14 @@ FORMATTER=clang-format -i -style=$(STYLE_BLUEPRINT)
 
 ## make build
 build: $(SRC)
-	$(CC) $(OPTIMIZED) $(DEBUG) $(SRC) -o $(OUTPUT)
+	$(CC) $(OPTIMIZED) $(DEBUG) $(SRC) -o $(OUT)
 
 format: $(SRC)
 	$(FORMATTER) $(SRC)
 
-test: $(OUTPUT)
-	/bin/echo -e "123\n45 67" | ./$(OUTPUT)
+test: $(OUT)
+	/bin/echo -e "123\n45 67" | ./$(OUT)
 	/bin/echo -n "" | ./wc
-	./$(OUTPUT) $(SRC)
-	./$(OUTPUT) nonexistent_file || true
+	/bin/echo "  xx x" | ./$(OUT) -w
+	./$(OUT) $(SRC)
+	./$(OUT) nonexistent_file || true
diff --git a/wc b/wc
Binary files differ.
diff --git a/wc.c b/wc.c
@@ -6,17 +6,22 @@ int process_fn(int fn)
 {
     char c[1];
 		int seen_word=0;
-		int seen_sep=0;
+		int seen_sep_after_word=0;
 		int num_words = 0;
     while (read(fn, c, sizeof(c)) > 0) {
-				if(*c == '\n' || *c == ' ' || *c == '\t'){
-					seen_sep = 1;
-				} else {
+				if(*c != '\n' && *c != ' ' && *c != '\t'){
 					seen_word = 1;
+				} else if(seen_word) {
+					seen_sep_after_word = 1;
+				} else {
+					// see a separator, but haven't seen a word: do nothing
+					// exercise: what happens if you only track seen_sep,
+					// instead of seen_sep_after_word?
+					// test with: $ echo " x x" | ./wc
 				}
-				if(seen_word && seen_sep){
+				if(seen_word && seen_sep_after_word){
 					num_words++;
-					seen_sep = seen_word = 0;
+					seen_sep_after_word = seen_word = 0;
 				}
     }
 		if(seen_word){
@@ -38,7 +43,8 @@ int main(int argc, char** argv)
         }
         return process_fn(fileno(fp));
     } else {
-        printf("To do");
+        printf("Usage: ww file.txt\n");
+				printf("   or: cat file.txt | ww\n");
     }
     return 0;
 }