badwords: check indented lines in source code, fix fallouts

- badwords.pl: add `-a` option to check all lines in source code files.
  Before this patch indented lines were skipped (to avoid Markdown code
  fences.)
- GHA/checksrc: use `-a` when verifying the source code.
- GHA/checksrc: disable `So` and `But` rules for source code.
- GHA/checksrc: add docs/examples to the verified sources.
- badwords.txt: delete 4 duplicates.
- badwords.txt: group and sort contractions.
- badwords.txt: allow ` url = `, `DIR`, `<file name`.

Closes curl#19536

Author: vszakats

.github/scripts/badwords.pl

@@ -20,7 +20,12 @@
 my @whitelist;
 my %alt;
 my %exactcase;
+my $skip_indented = 1;
 
+if($ARGV[0] eq "-a") {
+    shift @ARGV;
+    $skip_indented = 0;
+}
 my %wl;
 if($ARGV[0] eq "-w") {
     shift @ARGV;
@@ -68,7 +73,7 @@ sub file {
         my $in = $_;
         $l++;
         chomp $in;
-        if($in =~ /^    /) {
+        if($skip_indented && $in =~ /^    /) {
             next;
         }
         # remove the link part

.github/scripts/badwords.txt

@@ -10,59 +10,56 @@ tool chain:toolchain
 tool-chain:toolchain
 wild-card:wildcard
 wild card:wildcard
+\bit's:it is
+aren't:are not
+can't:cannot
+could've:could have
+couldn't:could not
+didn't:did not
+doesn't:does not
+don't=do not
 i'm:I am
-you've:You have
-we've:we have
-we're:we are
-we'll:we will
-we'd:we would
-they've:They have
-they're:They are
-they'll:They will
+isn't:is not
+it'd:it would
+should've:should have
+that's:that is
+there's:there is
 they'd:They would
-you've:you have
+they'll:They will
+they're:They are
+they've:They have
+we'd:we would
+we'll:we will
+we're:we are
+we've:we have
+won't:will not
 you'd:you would
 you'll:you will
 you're:you are
-should've:should have
-don't=do not
-could've:could have
-doesn't:does not
-isn't:is not
-aren't:are not
+you've:you have
  a html: an html
  a http: an http
  a ftp: an ftp
  a IPv4: an IPv4
  a IPv6: an IPv6
- url =URL
+ url [^=]=URL
 [^/]internet\b=Internet
 isation:ization
-\bit's:it is
-it'd:it would
-there's:there is
 [^.]\. And: Rewrite it somehow?
 ^(And|So|But) = Rewrite it somehow?
 \. But: Rewrite it somehow?
 \. So : Rewrite without "so" ?
- dir [^=]:directory
+ dir [^=]=directory
+ Dir [^=]=Directory
 sub-director:subdirector
-you'd:you would
-you'll:you will
-can't:cannot
-that's:that is
 web page:webpage
 host name\b:hostname
 host names\b:hostnames
-[^;]file name\b:filename
+[^;<]file name\b:filename
 file names\b:filenames
 \buser name\b:username
 \buser names\b:usernames
 \bpass phrase:passphrase
-didn't:did not
-doesn't:does not
-won't:will not
-couldn't:could not
 \bwill\b:rewrite to present tense
 \b32bit=32-bit
 \b64bit=64-bit

.github/workflows/checksrc.yml

@@ -174,6 +174,7 @@ jobs:
       - name: 'yamlcheck'
         run: .github/scripts/yamlcheck.sh
 
-      # we allow some extra in source code
       - name: 'badwords'
-        run: grep -Ev '(\\bwill)' .github/scripts/badwords.txt | .github/scripts/badwords.pl src lib include
+        run: |
+          # we allow some extra in source code
+          grep -Ev '(\\bwill| But: | So : )' .github/scripts/badwords.txt | .github/scripts/badwords.pl -a src lib include docs/examples

docs/examples/anyauthput.c

@@ -152,7 +152,7 @@ int main(int argc, char **argv)
        data twice!!! */
     curl_easy_setopt(curl, CURLOPT_HTTPAUTH, CURLAUTH_ANY);
 
-    /* set user name and password for the authentication */
+    /* set username and password for the authentication */
     curl_easy_setopt(curl, CURLOPT_USERPWD, "user:password");
 
     /* Now run off and do what you have been told! */

docs/examples/connect-to.c

@@ -40,7 +40,7 @@ int main(void)
   /*
     Each single string should be written using the format
     HOST:PORT:CONNECT-TO-HOST:CONNECT-TO-PORT where HOST is the host of the
-    request, PORT is the port of the request, CONNECT-TO-HOST is the host name
+    request, PORT is the port of the request, CONNECT-TO-HOST is the hostname
     to connect to, and CONNECT-TO-PORT is the port to connect to.
    */
   /* instead of curl.se:443, it resolves and uses example.com:443 but in other
@@ -53,12 +53,12 @@ int main(void)
     curl_easy_setopt(curl, CURLOPT_VERBOSE, 1L);
     curl_easy_setopt(curl, CURLOPT_URL, "https://curl.se/");
 
-    /* since this connects to the wrong host, checking the host name in the
+    /* since this connects to the wrong host, checking the hostname in the
        server certificate fails, so unless we disable the check libcurl
        returns CURLE_PEER_FAILED_VERIFICATION */
     curl_easy_setopt(curl, CURLOPT_SSL_VERIFYHOST, 0L);
 
-    /* Letting the wrong host name in the certificate be okay, the transfer
+    /* Letting the wrong hostname in the certificate be okay, the transfer
        goes through but (most likely) causes a 404 or similar because it sends
        an unknown name in the Host: header field */
     res = curl_easy_perform(curl);

docs/examples/cookie_interface.c

@@ -47,7 +47,7 @@ static int print_cookies(CURL *curl)
   printf("Cookies, curl knows:\n");
   res = curl_easy_getinfo(curl, CURLINFO_COOKIELIST, &cookies);
   if(res != CURLE_OK) {
-    fprintf(stderr, "Curl curl_easy_getinfo failed: %s\n",
+    fprintf(stderr, "curl curl_easy_getinfo failed: %s\n",
             curl_easy_strerror(res));
     return 1;
   }
@@ -85,7 +85,7 @@ main(void)
     curl_easy_setopt(curl, CURLOPT_COOKIEFILE, ""); /* start cookie engine */
     res = curl_easy_perform(curl);
     if(res != CURLE_OK) {
-      fprintf(stderr, "Curl perform failed: %s\n", curl_easy_strerror(res));
+      fprintf(stderr, "curl perform failed: %s\n", curl_easy_strerror(res));
       return 1;
     }
 
@@ -105,7 +105,7 @@ main(void)
              "PREF", "hello example, I like you!");
     res = curl_easy_setopt(curl, CURLOPT_COOKIELIST, nline);
     if(res != CURLE_OK) {
-      fprintf(stderr, "Curl curl_easy_setopt failed: %s\n",
+      fprintf(stderr, "curl curl_easy_setopt failed: %s\n",
               curl_easy_strerror(res));
       return 1;
     }
@@ -120,7 +120,7 @@ main(void)
       "expires=Sun, 17-Jan-2038 19:14:07 GMT; path=/; domain=.example.com");
     res = curl_easy_setopt(curl, CURLOPT_COOKIELIST, nline);
     if(res != CURLE_OK) {
-      fprintf(stderr, "Curl curl_easy_setopt failed: %s\n",
+      fprintf(stderr, "curl curl_easy_setopt failed: %s\n",
               curl_easy_strerror(res));
       return 1;
     }
@@ -129,14 +129,14 @@ main(void)
 
     res = curl_easy_perform(curl);
     if(res != CURLE_OK) {
-      fprintf(stderr, "Curl perform failed: %s\n", curl_easy_strerror(res));
+      fprintf(stderr, "curl perform failed: %s\n", curl_easy_strerror(res));
       return 1;
     }
 
     curl_easy_cleanup(curl);
   }
   else {
-    fprintf(stderr, "Curl init failed!\n");
+    fprintf(stderr, "curl init failed!\n");
     return 1;
   }
 

docs/examples/debug.c

@@ -69,7 +69,7 @@ static void dump(const char *text, FILE *stream, unsigned char *ptr,
       }
       fprintf(stream, "%c",
               (ptr[i + c] >= 0x20) && (ptr[i + c] < 0x80) ? ptr[i + c] : '.');
-      /* check again for 0D0A, to avoid an extra \n if it's at width */
+      /* check again for 0D0A, to avoid an extra \n if it is at width */
       if(nohex && (i + c + 2 < size) && ptr[i + c + 1] == 0x0D &&
          ptr[i + c + 2] == 0x0A) {
         i += (c + 3 - width);

docs/examples/ephiperfifo.c

@@ -133,7 +133,7 @@ static void mcode_or_die(const char *where, CURLMcode code)
 
 static void timer_cb(struct GlobalInfo *g, int revents);
 
-/* Update the timer after curl_multi library does its thing. Curl informs the
+/* Update the timer after curl_multi library does its thing. curl informs the
  * application through this callback what it wants the new timeout to be,
  * after it does some work. */
 static int multi_timer_cb(CURLM *multi, long timeout_ms, struct GlobalInfo *g)
@@ -219,7 +219,7 @@ static void timer_cb(struct GlobalInfo *g, int revents)
   err = read(g->tfd, &count, sizeof(uint64_t));
   if(err == -1) {
     /* Note that we may call the timer callback even if the timerfd is not
-     * readable. It's possible that there are multiple events stored in the
+     * readable. It is possible that there are multiple events stored in the
      * epoll buffer (i.e. the timer may have fired multiple times). The event
      * count is cleared after the first call so future events in the epoll
      * buffer fails to read from the timer. */

docs/examples/ftpupload.c

@@ -90,7 +90,7 @@ int main(void)
   /* get a FILE * of the file */
   hd_src = fopen(LOCAL_FILE, "rb");
   if(!hd_src) {
-    printf("Couldn't open '%s': %s\n", LOCAL_FILE, strerror(errno));
+    printf("Could not open '%s': %s\n", LOCAL_FILE, strerror(errno));
     return 2;
   }
 

docs/examples/htmltidy.c

@@ -50,7 +50,7 @@ void dumpNode(TidyDoc doc, TidyNode tnod, int indent)
   for(child = tidyGetChild(tnod); child; child = tidyGetNext(child) ) {
     ctmbstr name = tidyNodeGetName(child);
     if(name) {
-      /* if it has a name, then it's an HTML tag ... */
+      /* if it has a name, then it is an HTML tag ... */
       TidyAttr attr;
       printf("%*.*s%s ", indent, indent, "<", name);
       /* walk the attribute list */
@@ -62,7 +62,7 @@ void dumpNode(TidyDoc doc, TidyNode tnod, int indent)
       printf(">\n");
     }
     else {
-      /* if it does not have a name, then it's probably text, cdata, etc... */
+      /* if it does not have a name, then it is probably text, cdata, etc... */
       TidyBuffer buf;
       tidyBufInit(&buf);
       tidyNodeGetText(doc, child, &buf);