Update: rename whitespace functions to space functions and consider zero-width

Whitespace is now being used more explicitly in regards to UTF-8.

Zero-width consideratons added, but I think more work is needed in this regard.

diff --git a/level_1/fl_fss/c/fss.c b/level_1/fl_fss/c/fss.c
index 5288409b76de2da15a142970b6bfab67ad43ca8b..0144ec0da1fab3b3b96b04e5dcde5805caa6922f 100644 (file)
--- a/level_1/fl_fss/c/fss.c
+++ b/level_1/fl_fss/c/fss.c
@@ -291,8 +291,8 @@ extern "C" {
   }
 #endif // _di_fl_fss_is_space_
 
-#ifndef _di_fl_fss_skip_past_whitespace_
-  f_return_status fl_fss_skip_past_whitespace(const f_string_dynamic buffer, f_string_location *location) {
+#ifndef _di_fl_fss_skip_past_space_
+  f_return_status fl_fss_skip_past_space(const f_string_dynamic buffer, f_string_location *location) {
     #ifndef _di_level_1_parameter_checking_
       if (buffer.used <= 0) return f_status_set_error(f_invalid_parameter);
       if (location == 0) return f_status_set_error(f_invalid_parameter);
@@ -310,7 +310,7 @@ extern "C" {
       max_width = buffer.used - location->start;
     }
 
-    while (buffer.string[location->start] == f_string_eos || (status = f_utf_is_whitespace(buffer.string + location->start, max_width)) == f_true) {
+    while (buffer.string[location->start] == f_string_eos || (status = f_utf_is_whitespace(buffer.string + location->start, max_width)) == f_true || (status = f_utf_is_control(buffer.string + location->start, max_width)) == f_true) {
       if (f_status_is_error(status)) {
         return status;
       }
@@ -349,10 +349,10 @@ extern "C" {
 
     return f_none;
   }
-#endif // _di_fl_fss_skip_past_whitespace_
+#endif // _di_fl_fss_skip_past_space_
 
-#ifndef _di_fl_fss_skip_past_all_whitespace_
-  f_return_status fl_fss_skip_past_all_whitespace(const f_string_dynamic buffer, f_string_location *location) {
+#ifndef _di_fl_fss_skip_past_non_graph_
+  f_return_status fl_fss_skip_past_non_graph(const f_string_dynamic buffer, f_string_location *location) {
     #ifndef _di_level_1_parameter_checking_
       if (buffer.used <= 0) return f_status_set_error(f_invalid_parameter);
       if (location == 0) return f_status_set_error(f_invalid_parameter);
@@ -370,10 +370,8 @@ extern "C" {
       max_width = buffer.used - location->start;
     }
 
-    while (buffer.string[location->start] == f_string_eos || (status = f_utf_is_graph(buffer.string + location->start, max_width)) == f_false) {
-      if (f_status_is_error(status)) {
-        return status;
-      }
+    while (buffer.string[location->start] == f_string_eos || ((status = f_utf_is_graph(buffer.string + location->start, max_width)) == f_false && (status = f_utf_is_zero_width(buffer.string + location->start, max_width)) == f_false)) {
+      if (f_status_is_error(status)) return status;
 
       width = f_macro_utf_byte_width_is(buffer.string[location->start]);
 
@@ -407,7 +405,7 @@ extern "C" {
 
     return f_none;
   }
-#endif // _di_fl_fss_skip_past_all_whitespace_
+#endif // _di_fl_fss_skip_past_non_graph_
 
 #ifndef _di_fl_fss_shift_delimiters_
   f_return_status fl_fss_shift_delimiters(f_string_dynamic *buffer, const f_string_location location) {

diff --git a/level_1/fl_fss/c/fss.h b/level_1/fl_fss/c/fss.h
index 04e027ab87d6163bf681cd9addafa8596fbe4fb1..2c4efbbde47a8753776bf95d6c949e3b20f4bdc2 100644 (file)
--- a/level_1/fl_fss/c/fss.h
+++ b/level_1/fl_fss/c/fss.h
@@ -192,6 +192,9 @@ extern "C" {
 /**
  * Skip past all whitespace and control characters, except newline.
  *
+ * Zero-width characters are not skipped because they might be part of a graph character, such as combining characters.
+ * @todo needs consideration on how to handle zero-width before space/control vs zero-width before graph.
+ *
  * @param buffer
  *   The string to process.
  * @param location
@@ -202,12 +205,15 @@ extern "C" {
  *   f_none on success.
  *   f_invalid_parameter (with error bit) if a parameter is invalid.
  */
-#ifndef _di_fl_fss_skip_past_whitespace_
-  extern f_return_status fl_fss_skip_past_whitespace(const f_string_dynamic buffer, f_string_location *location);
-#endif // _di_fl_fss_skip_past_whitespace_
+#ifndef _di_fl_fss_skip_past_space_
+  extern f_return_status fl_fss_skip_past_space(const f_string_dynamic buffer, f_string_location *location);
+#endif // _di_fl_fss_skip_past_space_
 
 /**
- * Skip past all whitespace and control characters.
+ * Skip past all non-graph and non-zero-width characters (whitespace and control characters).
+ *
+ * Zero-width characters are not skipped because they might be part of a graph character, such as combining characters.
+ * @todo needs consideration on how to handle zero-width before space/control vs zero-width before graph.
  *
  * @param buffer
  *   The string to process.
@@ -219,9 +225,9 @@ extern "C" {
  *   f_none on success.
  *   f_invalid_parameter (with error bit) if a parameter is invalid.
  */
-#ifndef _di_fl_fss_skip_past_all_whitespace_
-  extern f_return_status fl_fss_skip_past_all_whitespace(const f_string_dynamic buffer, f_string_location *location);
-#endif // _di_fl_fss_skip_past_all_whitespace_
+#ifndef _di_fl_fss_skip_past_non_graph_
+  extern f_return_status fl_fss_skip_past_non_graph(const f_string_dynamic buffer, f_string_location *location);
+#endif // _di_fl_fss_skip_past_non_graph_
 
 #ifdef __cplusplus
 } // extern "C"

diff --git a/level_1/fl_fss/c/fss_basic.c b/level_1/fl_fss/c/fss_basic.c
index aeda4dcec786f5c87ae9bde2f066194277750180..0248a5e2eeca1ad40cbc5d7da9845ee745fb5a0e 100644 (file)
--- a/level_1/fl_fss/c/fss_basic.c
+++ b/level_1/fl_fss/c/fss_basic.c
@@ -21,7 +21,7 @@ extern "C" {
     // delimits must only be applied once a valid object is found
     f_string_lengths delimits = f_string_lengths_initialize;
 
-    fl_fss_skip_past_whitespace(*buffer, location);
+    fl_fss_skip_past_space(*buffer, location);
     fl_macro_fss_object_return_on_overflow((*buffer), (*location), (*found), delimits, f_no_data_on_eos, f_no_data_on_stop)
 
     // return found nothing if this line only contains whitespace and delimit placeholders
@@ -385,7 +385,7 @@ extern "C" {
     // delimits must only be applied once a valid object is found
     f_string_lengths delimits = f_string_lengths_initialize;
 
-    fl_fss_skip_past_whitespace(*buffer, location);
+    fl_fss_skip_past_space(*buffer, location);
     fl_macro_fss_content_return_on_overflow((*buffer), (*location), (*found), delimits, f_none_on_eos, f_none_on_stop)
 
     // return found nothing if this line only contains whitespace and delimit placeholders

diff --git a/level_1/fl_fss/c/fss_basic_list.c b/level_1/fl_fss/c/fss_basic_list.c
index bb3a1ec6e9e9355fc2a88c756daf0e6d22d9ff88..576e42b1e9eff1b22ebadd40834da6254dabb688 100644 (file)
--- a/level_1/fl_fss/c/fss_basic_list.c
+++ b/level_1/fl_fss/c/fss_basic_list.c
@@ -21,7 +21,7 @@ extern "C" {
     // delimits must only be applied once a valid object is found.
     f_string_lengths delimits = f_string_lengths_initialize;
 
-    fl_fss_skip_past_whitespace(*buffer, location);
+    fl_fss_skip_past_space(*buffer, location);
     fl_macro_fss_object_return_on_overflow((*buffer), (*location), (*found), delimits, f_no_data_on_eos, f_no_data_on_stop)
 
     // return found nothing if this line only contains whitespace and delimit placeholders.

diff --git a/level_1/fl_fss/c/fss_extended.c b/level_1/fl_fss/c/fss_extended.c
index b19bd98aba717fc98a90f42dd4c3cf3a82c81335..77ca67433cc95ac8d86760b8cc7b0a7cef8d8a82 100644 (file)
--- a/level_1/fl_fss/c/fss_extended.c
+++ b/level_1/fl_fss/c/fss_extended.c
@@ -21,7 +21,7 @@ extern "C" {
     // delimits must only be applied once a valid object is found
     f_string_lengths delimits = f_string_lengths_initialize;
 
-    fl_fss_skip_past_whitespace(*buffer, location);
+    fl_fss_skip_past_space(*buffer, location);
     fl_macro_fss_object_return_on_overflow((*buffer), (*location), (*found), delimits, f_no_data_on_eos, f_no_data_on_stop)
 
     // return found nothing if this line only contains whitespace and delimit placeholders
@@ -377,7 +377,7 @@ extern "C" {
     // delimits must only be applied once a valid object is found
     f_string_lengths delimits = f_string_lengths_initialize;
 
-    fl_fss_skip_past_whitespace(*buffer, location);
+    fl_fss_skip_past_space(*buffer, location);
     fl_macro_fss_content_return_on_overflow((*buffer), (*location), (*found), delimits, f_none_on_eos, f_none_on_stop)
 
     // return found nothing if this line only contains whitespace and delimit placeholders

diff --git a/level_1/fl_fss/c/fss_extended_list.c b/level_1/fl_fss/c/fss_extended_list.c
index b0c1e25951a2543f84f4bd8d4a49851a783277e6..87415e2f8a4386ac77d80b8e500cce89d1150c56 100644 (file)
--- a/level_1/fl_fss/c/fss_extended_list.c
+++ b/level_1/fl_fss/c/fss_extended_list.c
@@ -21,7 +21,7 @@ extern "C" {
     // delimits must only be applied once a valid object is found.
     f_string_lengths delimits = f_string_lengths_initialize;
 
-    fl_fss_skip_past_whitespace(*buffer, location);
+    fl_fss_skip_past_space(*buffer, location);
     fl_macro_fss_object_return_on_overflow((*buffer), (*location), (*found), delimits, f_no_data_on_eos, f_no_data_on_stop)
 
     // return found nothing if this line only contains whitespace and delimit placeholders.