lcompilers · Thirumalai-Shaktivel · Mar 14, 2024 · Mar 7, 2024 · Mar 7, 2024 · Mar 7, 2024
diff --git a/integration_tests/test_str_attributes.py b/integration_tests/test_str_attributes.py
@@ -354,6 +354,42 @@ def is_title():
     assert " ".istitle() == False
 
 def is_space():
+    s0: str = ""
+    assert s0.isspace() == False
+    assert "".isspace() == False
+
+    s1: str = " \t\n\v\f\r"
+    assert s1.isspace() == True
+    assert " \t\n\v\f\r".isspace() == True
+
+    s2: str = " \t\n\v\f\rabcd"
+    assert s2.isspace() == False
+    assert " \t\n\v\f\rabcd".isspace() == False
+
+    s3: str = "abcd \t\n\v\f\ref"
+    assert s3.isspace() == False
+    assert "abcd \t\n\v\f\ref".isspace() == False
+
+    s4: str = " \\t\n\v\f\r"
+    assert s4.isspace() == False
+    assert " \\t\n\v\f\r".isspace() == False
+
+    s5: str = " \\t\\n\\v\\f\\r"
+    assert s5.isspace() == False
+    assert " \\t\\n\\v\\f\\r".isspace() == False
+
+    s6: str = "Hello, LPython!\n"
+    assert s6.isspace() == False
+    assert "Hello, LPython!\n".isspace() == False
+
+    s7: str = "\t\tHello! \n"
+    assert s7.isspace() == False
+    assert "\t\tHello! \n".isspace() == False
+
+    s8: str = " \t \n \v \f \r "
+    assert s8.isspace() == True
+    assert " \t \n \v \f \r ".isspace() == True
+
     assert "\n".isspace() == True
     assert "    ".isspace() == True
     assert "\r".isspace() == True

diff --git a/src/libasr/string_utils.cpp b/src/libasr/string_utils.cpp
@@ -192,6 +192,9 @@ char* str_unescape_c(Allocator &al, LCompilers::Str &s) {
         } else if (s[idx] == '\\' && s[idx+1] == 'v') {
             x += "\v";
             idx++;
+        } else if (s[idx] == '\\' && s[idx + 1] == 'f') {
+            x += "\f";
+            idx++;
         } else if (s[idx] == '\\' && s[idx+1] == '\\') {
             x += "\\";
             idx++;

diff --git a/src/runtime/lpython_builtin.py b/src/runtime/lpython_builtin.py
@@ -805,8 +805,6 @@ def _lpython_str_istitle(s: str) -> bool:
 
     return True if not only_whitespace else False
 
-
-
 @overload
 def _lpython_str_find(s: str, sub: str) -> i32:
     s_len :i32; sub_len :i32; flag: bool; _len: i32;
@@ -1051,16 +1049,42 @@ def _lpython_str_isascii(s: str) -> bool:
             return False
     return True
 
-def _lpython_str_isspace(s:str) -> bool:
+def _lpython_str_isspace(s: str) -> bool:
+    # A Unicode character is considered a 'whitespace' if it has has a bidirectional
+    # type 'WS', 'B' or 'S'; or the category 'Zs'.
     if len(s) == 0:
         return False
-    ch: str 
+
+    ch: str
     for ch in s:
-        if ch != ' ' and ch != '\t' and ch != '\n' and ch != '\r' and ch != '\f' and ch != '\v':
+        if not (ch == " "  or   # SPACE
+            ch == "\n"     or   # LINE FEED (LF)
+            ch == "\r"     or   # CARRIAGE RETURN (CR)
+            ch == "\t"     or   # CHARACTER TABULATION (HT)
+            ch == "\v"     or   # VERTICAL TAB (VT)
+            ch == "\f"     or   # FORM FEED (FF)
+            ch == "\u00A0" or   # NO-BREAK SPACE
+            ch == "\u1680" or   # OGHAM SPACE MARK
+            ch == "\u2000" or   # EN QUAD
+            ch == "\u2001" or   # EM QUAD
+            ch == "\u2002" or   # EN SPACE
+            ch == "\u2003" or   # EM SPACE
+            ch == "\u2004" or   # THREE-PER-EM SPACE
+            ch == "\u2005" or   # FOUR-PER-EM SPACE
+            ch == "\u2006" or   # SIX-PER-EM SPACE
+            ch == "\u2007" or   # FIGURE SPACE
+            ch == "\u2008" or   # PUNCTUATION SPACE
+            ch == "\u2009" or   # THIN SPACE
+            ch == "\u200A" or   # HAIR SPACE
+            ch == "\u2028" or   # LINE SEPARATOR
+            ch == "\u2029" or   # PARAGRAPH SEPARATOR
+            ch == "\u202F" or   # NARROW NO-BREAK SPACE
+            ch == "\u205F" or   # MEDIUM MATHEMATICAL SPACE
+            ch == "\u3000"      # IDEOGRAPHIC SPACE
+        ):
             return False
     return True
 
-
 def list(s: str) -> list[str]:
     l: list[str] = []
     i: i32
@@ -1069,3 +1093,4 @@ def list(s: str) -> list[str]:
     for i in range(len(s)):
         l.append(s[i])
     return l
+