Add SyntaxQ and add a new "String Tests" Section

.pre-commit-config.yaml

@@ -6,17 +6,17 @@ repos:
     hooks:
     - id: check-merge-conflict
     - id: debug-statements
-      stages: [commit]
+      stages: [pre-commit]
     - id: end-of-file-fixer
-      stages: [commit]
+      stages: [pre-commit]
 -   repo: https://github.com/pycqa/isort
     rev: 5.13.2
     hooks:
       - id: isort
-        stages: [commit]
+        stages: [pre-commit]
 -   repo: https://github.com/psf/black
     rev: 23.12.1
     hooks:
     - id: black
       language_version: python3
-      stages: [commit]
+      stages: [pre-commit]

mathics/builtin/atomic/strings.py

@@ -15,26 +15,22 @@
 
 from mathics.core.atoms import Integer, Integer0, Integer1, String
 from mathics.core.attributes import A_LISTABLE, A_PROTECTED
-from mathics.core.builtin import Builtin, Predefined, PrefixOperator, Test
+from mathics.core.builtin import Builtin, Predefined, PrefixOperator
 from mathics.core.convert.expression import to_mathics_list
-from mathics.core.convert.python import from_bool
-from mathics.core.convert.regex import to_regex
 from mathics.core.evaluation import Evaluation
 from mathics.core.expression import Expression
 from mathics.core.list import ListExpression
 from mathics.core.parser import MathicsFileLineFeeder, parse
-from mathics.core.symbols import Symbol, SymbolTrue
 from mathics.core.systemsymbols import (
     SymbolFailed,
     SymbolInputForm,
     SymbolNone,
     SymbolOutputForm,
+    SymbolToExpression,
 )
-from mathics.eval.strings import eval_ToString
+from mathics.eval.strings import eval_StringContainsQ, eval_ToString
 from mathics.settings import SYSTEM_CHARACTER_ENCODING
 
-SymbolToExpression = Symbol("ToExpression")
-
 # covers all of the variations. Here we just give some minimal basics
 
 # Data taken from:
@@ -130,48 +126,6 @@ def push(i, iter, form):
         push(i, iter, form)
 
 
-def _pattern_search(name, string, patt, evaluation, options, matched):
-    # Get the pattern list and check validity for each
-    if patt.has_form("List", None):
-        patts = patt.elements
-    else:
-        patts = [patt]
-    re_patts = []
-    for p in patts:
-        py_p = to_regex(p, show_message=evaluation.message)
-        if py_p is None:
-            evaluation.message("StringExpression", "invld", p, patt)
-            return
-        re_patts.append(py_p)
-
-    flags = re.MULTILINE
-    if options["System`IgnoreCase"] is SymbolTrue:
-        flags = flags | re.IGNORECASE
-
-    def _search(patts, str, flags, matched):
-        if any(re.search(p, str, flags=flags) for p in patts):
-            return from_bool(matched)
-        return from_bool(not matched)
-
-    # Check string validity and perform regex searchhing
-    if string.has_form("List", None):
-        py_s = [s.get_string_value() for s in string.elements]
-        if any(s is None for s in py_s):
-            evaluation.message(
-                name, "strse", Integer1, Expression(Symbol(name), string, patt)
-            )
-            return
-        return to_mathics_list(*[_search(re_patts, s, flags, matched) for s in py_s])
-    else:
-        py_s = string.get_string_value()
-        if py_s is None:
-            evaluation.message(
-                name, "strse", Integer1, Expression(Symbol(name), string, patt)
-            )
-            return
-        return _search(re_patts, py_s, flags, matched)
-
-
 def anchor_pattern(patt):
     """
     anchors a regex in order to force matching against an entire string.
@@ -691,35 +645,11 @@ class StringContainsQ(Builtin):
 
     def eval(self, string, patt, evaluation: Evaluation, options: dict):
         "StringContainsQ[string_, patt_, OptionsPattern[%(name)s]]"
-        return _pattern_search(
+        return eval_StringContainsQ(
             self.__class__.__name__, string, patt, evaluation, options, True
         )
 
 
-class StringQ(Test):
-    """
-    <url>
-    :WMA link:
-    https://reference.wolfram.com/language/ref/StringQ.html</url>
-    <dl>
-      <dt>'StringQ[$expr$]'
-      <dd>returns 'True' if $expr$ is a 'String', or 'False' otherwise.
-    </dl>
-
-    >> StringQ["abc"]
-     = True
-    >> StringQ[1.5]
-     = False
-    >> Select[{"12", 1, 3, 5, "yz", x, y}, StringQ]
-     = {12, yz}
-    """
-
-    summary_text = "test whether an expression is a string"
-
-    def test(self, expr) -> bool:
-        return isinstance(expr, String)
-
-
 class StringRepeat(Builtin):
     """
     <url>

mathics/builtin/string/__init__.py

@@ -2,3 +2,4 @@
 Strings and Characters
 
 """
+# FIXME: Redo. This is a Tech note, not a Guide Section.

mathics/builtin/string/characters.py

@@ -2,7 +2,7 @@
 """
 Characters in Strings
 """
-
+# FIXME: Redo: this is part of a Tech note, not a guide section.
 
 from mathics.core.atoms import String
 from mathics.core.attributes import A_LISTABLE, A_PROTECTED, A_READ_PROTECTED
@@ -72,74 +72,6 @@ def eval(self, start, stop, evaluation: Evaluation):
         return ListExpression(*[String(chr(code)) for code in range(start, stop + 1)])
 
 
-class DigitQ(Builtin):
-    """
-    <url>
-    :WMA link:
-    https://reference.wolfram.com/language/ref/DigitQ.html</url>
-
-    <dl>
-      <dt>'DigitQ[$string$]'
-      <dd>yields 'True' if all the characters in the $string$ are \
-          digits, and yields 'False' otherwise.
-
-    </dl>
-
-    >> DigitQ["9"]
-     = True
-
-    >> DigitQ["a"]
-     = False
-
-    >> DigitQ["01001101011000010111010001101000011010010110001101110011"]
-     = True
-
-    >> DigitQ["-123456789"]
-     = False
-
-    """
-
-    rules = {
-        "DigitQ[string_]": (
-            "If[StringQ[string], StringMatchQ[string, DigitCharacter...], False, False]"
-        ),
-    }
-    summary_text = "test whether all the characters are digits"
-
-
-class LetterQ(Builtin):
-    """
-    <url>
-    :WMA link:
-    https://reference.wolfram.com/language/ref/LetterQ.html</url>
-
-    <dl>
-      <dt>'LetterQ[$string$]'
-      <dd> yields 'True' if all the characters in the $string$ are \
-           letters, and yields 'False' otherwise.
-    </dl>
-
-    >> LetterQ["m"]
-     = True
-
-    >> LetterQ["9"]
-     = False
-
-    >> LetterQ["Mathics"]
-     = True
-
-    >> LetterQ["Welcome to Mathics"]
-     = False
-    """
-
-    rules = {
-        "LetterQ[string_]": (
-            "If[StringQ[string], StringMatchQ[string, LetterCharacter...], False, False]"
-        ),
-    }
-    summary_text = "test whether all the characters are letters"
-
-
 class LowerCaseQ(Test):
     """
     <url>:WMA link:https://reference.wolfram.com/language/ref/LowerCaseQ.html</url>
@@ -159,8 +91,10 @@ class LowerCaseQ(Test):
 
     summary_text = "test whether all the characters are lower-case letters"
 
-    def test(self, s) -> bool:
-        return isinstance(s, String) and all(c.islower() for c in s.get_string_value())
+    def test(self, expr) -> bool:
+        return isinstance(expr, String) and all(
+            c.islower() for c in expr.get_string_value()
+        )
 
 
 class ToLowerCase(Builtin):
@@ -224,5 +158,7 @@ class UpperCaseQ(Test):
 
     summary_text = "test whether all the characters are upper-case letters"
 
-    def test(self, s) -> bool:
-        return isinstance(s, String) and all(c.isupper() for c in s.get_string_value())
+    def test(self, expr) -> bool:
+        return isinstance(expr, String) and all(
+            c.isupper() for c in expr.get_string_value()
+        )

mathics/builtin/string/operations.py

@@ -11,7 +11,6 @@
     _parallel_match,
     _StringFind,
     mathics_split,
-    to_regex,
 )
 from mathics.core.atoms import Integer, Integer1, Integer3, String
 from mathics.core.attributes import (
@@ -23,6 +22,7 @@
 )
 from mathics.core.builtin import Builtin, InfixOperator
 from mathics.core.convert.python import from_python
+from mathics.core.convert.regex import to_regex
 from mathics.core.evaluation import Evaluation
 from mathics.core.expression import BoxError, Expression, string_list
 from mathics.core.expression_predefined import MATHICS3_INFINITY