From 5ad1054634e2e38e3ba968feec206f4442fc11e4 Mon Sep 17 00:00:00 2001
From: "Meredith L. Patterson" <mlp@thesmartpolitenerd.com>
Date: Sat, 16 Nov 2013 00:55:41 +0100
Subject: [PATCH] First cut at PHP bindings; no tests yet.
---
src/bindings/php/hammer.xml | 604 ++++++++++++++++++++++++++++++++++++
1 file changed, 604 insertions(+)
create mode 100644 src/bindings/php/hammer.xml
diff --git a/src/bindings/php/hammer.xml b/src/bindings/php/hammer.xml
new file mode 100644
index 00000000..21722925
--- /dev/null
+++ b/src/bindings/php/hammer.xml
@@ -0,0 +1,604 @@
+<?xml version="1.0" ?>
+<!DOCTYPE extension SYSTEM "../extension.dtd">
+<extension name="hammer" version="1.1.3">
+ <summary>A library for defining parsers (character- or binary-oriented) inline.</summary>
+ <description>...</description>
+
+ <maintainers>
+ <maintainer>
+ <user>mlp</user>
+ <name>Meredith L. Patterson</name>
+ <email>mlp@upstandinghackers.com</email>
+ <role>lead</role>
+ </maintainer>
+ </maintainers>
+
+ <license>LGPL</license>
+
+ <release>
+ <version>0.1</version>
+ <date>2013-11-15</date>
+ <state>alpha</state>
+ <notes>First cut of extension.</notes>
+ </release>
+
+ <deps language="c" platform="unix">
+ <with testfile="include/hammer/hammer.h">Hammer C library</with>
+ <header name="allocator.h"/>
+ <header name="glue.h"/>
+ <header name="hammer.h"/>
+ <lib name="hammer" platform="unix"/>
+ </deps>
+
+ <class name="HParseResult">
+ <property name="ast"/>
+ <property name="type" type="string"/>
+ <!-- not sure we actually need this -->
+ <function name="free">
+ <proto>void free()</proto>
+ <summary>Deallocate a parse result</summary>
+ <description>
+ Free the memory allocated to a parse result when the result is no longer needed.
+ </description>
+ <code>
+ </code>
+ </function>
+ </class>
+
+ <class name="HBenchmarkResults">
+ <function name="report">
+ <proto>void report()</proto>
+ <summary>Output benchmarking results in a human-readable format</summary>
+ <description>
+ </description>
+ <code>
+ </code>
+ </function>
+ </class>
+
+ <class name="HParser">
+ <function name="parse">
+ <proto>HParseResult parse(string input)</proto>
+ <summary>Parse an input</summary>
+ <description>Top-level function to call a parser that has been built over some piece of input.</description>
+ <code>
+ </code>
+ </function>
+ <function name="compile">
+ <proto>int compile(string backend, array params)</proto>
+ <summary>Generate parse tables for the given parsing backend</summary>
+ <description>
+ Some of the parsing backends must transform a parser into a set of parse tables before they can be used. See the documentation for the parser backend in question for information about the [params] parameter, or pass in NULL for the defaults.
+
+ Returns -1 if the grammar cannot be compiled with the specified options; 0 otherwise.
+ </description>
+ <code>
+ </code>
+ </function>
+ <function name="benchmark">
+ <proto>object benchmark(array testcases)</proto>
+ <summary>Benchmark this parser using all the applicable parsing backends against a set of test cases you provide</summary>
+ <description>
+ </description>
+ <code>
+ </code>
+ </function>
+ </class>
+
+ <function role="public" name="hammer_token">
+ <proto>HParseResult hammer_token(string token)</proto>
+ <summary>Parse a token (primitive)</summary>
+ <description>
+ Given a string, returns a parser that parses that string value.
+
+ Result token type: string
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_ch">
+ <proto>HParseResult hammer_ch(string ch)</proto>
+ <summary>Parse a character (primitive)</summary>
+ <description>
+ Given a single character, returns a parser that parses that character.
+
+ Result token type: string
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_ch_range">
+ <proto>HParseResult hammer_ch_range(string lower, string upper)</proto>
+ <summary>Parse a character within the given range (primitive)</summary>
+ <description>
+ Given two single-character bounds, lower and upper, returns a parser that parses a single character within the range [lower, upper] (inclusive).
+
+ Result token type: string
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_int_range">
+ <proto>HParseResult hammer_int_range(HParser p, int lower, int upper)</proto>
+ <summary>Parse an integer within the given range (primitive)</summary>
+ <description>
+ Given an integer parser, p, and two integer bounds, lower and upper, returns a parser that parses an integral value within the range [lower, upper] (inclusive).
+
+ Result token type: int
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_bits">
+ <proto>HParseResult hammer_bits(int len, bool sign)</proto>
+ <summary>Parse a specified number of bits (primitive)</summary>
+ <description>
+ Returns a parser that parses the specified number of bits. sign == true if signed, false if unsigned.
+
+ Result token type: int
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_int64">
+ <proto>HParseResult hammer_int64()</proto>
+ <summary>Parse a 64-bit signed integer (primitive)</summary>
+ <description>
+ Returns a parser that parses a signed 8-byte integer value.
+
+ Result token type: int
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_int32">
+ <proto>HParseResult hammer_int32()</proto>
+ <summary>Parse a 32-bit signed integer (primitive)</summary>
+ <description>
+ Returns a parser that parses a signed 4-byte integer value.
+
+ Result token type: int
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_int16">
+ <proto>HParseResult hammer_int16()</proto>
+ <summary>Parse a 16-bit signed integer (primitive)</summary>
+ <description>
+ Returns a parser that parses a signed 2-byte integer value.
+
+ Result token type: int
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_int8">
+ <proto>HParseResult hammer_int8()</proto>
+ <summary>Parse an 8-bit signed integer (primitive)</summary>
+ <description>
+ Returns a parser that parses a signed 1-byte integer value.
+
+ Result token type: int
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_uint64">
+ <proto>HParseResult hammer_uint64()</proto>
+ <summary>Parse a 64-bit unsigned integer (primitive)</summary>
+ <description>
+ Returns a parser that parses an unsigned 8-byte integer value.
+
+ Result token type: int
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_uint32">
+ <proto>HParseResult hammer_uint32()</proto>
+ <summary>Parse a 32-bit unsigned integer (primitive)</summary>
+ <description>
+ Returns a parser that parses an unsigned 4-byte integer value.
+
+ Result token type: int
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_uint16">
+ <proto>HParseResult hammer_uint16()</proto>
+ <summary>Parse a 16-bit unsigned integer (primitive)</summary>
+ <description>
+ Returns a parser that parses an unsigned 2-byte integer value.
+
+ Result token type: int
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_uint8">
+ <proto>HParseResult hammer_uint8()</proto>
+ <summary>Parse an 8-bit unsigned integer (primitive)</summary>
+ <description>
+ Returns a parser that parses an unsigned 1-byte integer value.
+
+ Result token type: int
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_whitespace">
+ <proto>HParseResult hammer_whitespace(HParser p)</proto>
+ <summary>Parse something preceded by whitespace (higher-order)</summary>
+ <description>
+ Given a parser, p, returns a parser that skips any whitespace and then applies p.
+
+ Result token type: p's result type
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_left">
+ <proto>HParseResult hammer_left(HParser p, HParser q)</proto>
+ <summary>Take the leftmost result of two parsers (higher-order)</summary>
+ <description>
+ Given two parsers, p and q, returns a parser that parses them in sequence but only returns p's result.
+
+ Result token type: p's result type
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_right">
+ <proto>HParseResult hammer_right(HParser p, HParser q)</proto>
+ <summary>Take the rightmost result of two parsers (higher-order)</summary>
+ <description>
+ Given two parsers, p and q, returns a parser that parses them in sequence but only returns q's result.
+
+ Result token type: q's result type
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_middle">
+ <proto>HParseResult hammer_middle(HParser p, HParser x, HParser q)</proto>
+ <summary>Take the middle result of three parsers (higher-order)</summary>
+ <description>
+ Given three parsers, p, x, and q, returns a parser that parses them in sequence but only returns x's result.
+
+ Result token type: x's result type
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_action">
+ <proto>HParseResult hammer_action(HParser p, callable f)</proto>
+ <summary>Attach a semantic action to a parser (higher-order)</summary>
+ <description>
+ Given another parser, p, and a function, f, returns a parser that applies p, then applies f to everything in the AST of p's result.
+
+ Result token type: any
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_in">
+ <proto>HParseResult hammer_in(string charset)</proto>
+ <summary>Parse a character that appears in charset (primitive)</summary>
+ <description>
+ Parse a single character in the given charset.
+
+ Result token type: string
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_not_in">
+ <proto>HParseResult hammer_not_in(string charset)</proto>
+ <summary>Parse a character that does not appear in charset (primitive)</summary>
+ <description>
+ Parse a single character *not* in the given charset.
+
+ Result token type: string
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_end_p">
+ <proto>HParseResult hammer_end_p()</proto>
+ <summary>Recognize the end-of-input (primitive)</summary>
+ <description>
+ A no-argument parser that succeeds if there is no more input to parse.
+
+ Result token type: none.
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_nothing_p">
+ <proto>HParseResult hammer_nothing_p()</proto>
+ <summary>This parser always fails (primitive)</summary>
+ <description>
+ hammer_nothing_p is primarily useful when stubbing out a larger parser. If you define a rule as hammer_nothing_p(), the top-level parser will run, but if a rule containing hammer_nothing_p is invoked, the parse will fail.
+
+ Result token type: there is no result token for this parser.
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_sequence">
+ <proto>HParseResult hammer_sequence(array p_array)</proto>
+ <summary>Apply a list of parsers sequentially (higher-order)</summary>
+ <description>
+ Given an array of parsers, p_array, apply each parser in order. The parse succeeds only if all parsers succeed.
+
+ Result token type: array
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_choice">
+ <proto>HParseResult hammer_choice(array p_array)</proto>
+ <summary>Apply any one of a list of parsers (higher-order)</summary>
+ <description>
+ Given an array of parsers, p_array, apply each parser in order. The first parser to succeed produces the result; if no parsers succeed, the parse fails.
+
+ Result token type: the type of the first successful parser's result
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_butnot">
+ <proto>HParseResult hammer_butnot(HParser p1, HParser p2)</proto>
+ <summary>Parse p1 but not p2 (higher-order)</summary>
+ <description>
+ Given two parsers, p1 and p2, this parser succeeds in the following cases:
+
+ * if p1 succeeds and p2 fails (starting from the same place in the input stream)
+ * if both succeed but p1's result is as long as or longer than p2's
+
+ Result token type: p1's result type.
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_difference">
+ <proto>HParseResult hammer_difference(HParser p1, HParser p2)</proto>
+ <summary>Parse p1 but not p2 (higher-order)</summary>
+ <description>
+ Given two parsers, p1 and p2, this parser succeeds in the following cases:
+
+ * if p1 succeeds and p2 fails (starting from the same place in the input stream)
+ * if both succeed but p2's result is *strictly* shorter than p1's
+
+ Result token type: p1's result type.
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_xor">
+ <proto>HParseResult hammer_xor(HParser p1, HParser p2)</proto>
+ <summary>Parse p1 or p2 but not both (higher-order)</summary>
+ <description>
+ Given two parsers, p1 and p2, this parser suceeds if *either* p1 or p2 succeed, but not if they both do.
+
+ Result token type: the result type of whichever parser succeeded
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_many">
+ <proto>HParseResult hammer_many(HParser p)</proto>
+ <summary>Parse zero or more instances of p (higher-order)</summary>
+ <description>
+ Given a parser, p, this parser succeeds for zero or more repetitions of p.
+
+ Result token type: array
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_many1">
+ <proto>HParseResult hammer_many1(HParser p)</proto>
+ <summary>Parse one or more instances of p (higher-order)</summary>
+ <description>
+ Given a parser, p, this parser succeeds for one or more repetitions of p.
+
+ Result token type: array
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_repeat_n">
+ <proto>HParseResult hammer_repeat_n(HParser p, int n)</proto>
+ <summary>Parse exactly n instances of p (higher-order)</summary>
+ <description>
+ Given a parser, p, this parser succeeds for exactly N repetitions of p.
+
+ Result token type: array
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_optional">
+ <proto>HParseResult hammer_optional(HParser p)</proto>
+ <summary>Mark a parser as optional, like ? in regular expressions (higher-order)</summary>
+ <description>
+ Given a parser, p, this parser succeeds with the value p parsed or with an empty result.
+
+ Result token type: If p succeeded, the type of its result; if not, nothing.
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_ignore">
+ <proto>HParseResult hammer_ignore(HParser p)</proto>
+ <summary>Apply p but leave its result out of the final AST (higher-order)</summary>
+ <description>
+ Given a parser, p, this parser succeeds if p succeeds, but doesn't include p's result in the final result.
+
+ Result token type: none.
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_sepBy">
+ <proto>HParseResult hammer_sepBy(HParser p, HParser sep)</proto>
+ <summary>Parse a (possibly empty) sequence of values separated by a separator (higher-order)</summary>
+ <description>
+ Given a parser, p, and a parser for a separator, sep, this parser matches a (possibly empty) list of things that p can parse, separated by sep. For example, if p is hammer_many1(hammer_ch_range('0', '9')) and sep is hammer_ch(','), hammer_sepBy(p, sep) will match a comma-separated list of integers.
+
+ Result token type: array
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_sepBy1">
+ <proto>HParseResult hammer_sepBy1(HParser p, HParser sep)</proto>
+ <summary>Parse a sequence of values separated by a separator (higher-order)</summary>
+ <description>
+ Given a parser, p, and a parser for a separator, sep, this parser matches a list of things that p can parse, separated by sep. Unlike hammer_sepBy, this ensures that the result has at least one element. For example, if p is hammer_many(hammer_ch_range('0', '9')), hammer_sepBy1(p, sep) will match a comma-separated list of integers.
+
+ Result token type: array
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_epsilon_p">
+ <proto>HParseResult hammer_epsilon_p()</proto>
+ <summary>Parse the empty string (primitive)</summary>
+ <description>
+ This parser always returns a zero-length match, i.e., the empty string.
+
+ Result token type: none
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_length_value">
+ <proto>HParseResult hammer_length_value(HParser length, HParser value)</proto>
+ <summary>Parse (length) repetitions of (value) (higher-order)</summary>
+ <description>
+ This parser applies its first argument to read an unsigned integer value, then applies its second argument that many times. length should produce an integer value; this is checked at runtime. Specifically, length's token type must be int.
+
+ Result token type: array
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_attr_bool">
+ <proto>HParseResult hammer_attr_bool(HParser p, callable pred)</proto>
+ <summary>Ensure that some property holds for the AST (higher-order)</summary>
+ <description>
+ This parser attaches a predicate function, which returns true or false, to a parser. The function is evaluated over the parser's result. The parse only succeeds if pred returns true.
+
+ hammer_attr_bool will check whether p's result exists and whether p's result AST exists; you do not need to check for this in your predicate function.
+
+ Result token type: p's result type if pred succeeds, otherwise the parse fails.
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_and">
+ <proto>HParseResult hammer_and(HParser p)</proto>
+ <summary>Verify that p succeeds, but don't actually apply it (higher-order)</summary>
+ <description>
+ This parser asserts that a conditional syntax is satisfied, but doesn't consume that conditional syntax. This is useful for lookahead. As an example:
+
+ Suppose you already have a parser, hex_p, that parses numbers in hexadecimal format (including the leading "0x"). Then
+
+ hammer_sequence(hammer_and(hammer_token("0x")), hex_p)
+
+ checks to see whether there is a leading "0x", does not consume the "0x", then applies hex_p to parse the hexadecimal number.
+
+ This parser succeeds if p succeeds, and fails if p fails.
+
+ Result token type: none
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_not">
+ <proto>HParseResult hammer_not(HParser p)</proto>
+ <summary>Verify that p does not succeed, and don't consume any input (higher-order)</summary>
+ <description>
+ This parser asserts that a conditional syntax is *not* satisfied, and doesn't consume the additional syntax. As a somewhat contrived example:
+
+ Since hammer_choice applies its arguments in order, the following parser:
+
+ hammer_sequence(hammer_ch('a'), hammer_choice(hammer_ch('+'), hammer_token('++')), hammer_ch('b'))
+
+ will not parse "a++b", because once hammer_choice has succeeded, it will not backtrack and try other alternatives if a later parser in the sequence fails. Instead, you can force the use of the second alternative by turning the hammer_ch('+') alternative into a sequence with hammer_not:
+
+ hammer_sequence(hammer_ch('a'), hammer_choice(hammer_sequence(hammer_ch('+'), hammer_not('+')), hammer_token('++')), hammer_ch('b'))
+
+ If the input string is "a+b", the first alternative is applied; if the input string is "a++b", the second alternative is applied.
+
+ Result token type: none
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_indirect">
+ <proto>HParseResult hammer_indirect()</proto>
+ <summary>Forward-declare a parser to be used recursively (higher-order)</summary>
+ <description>
+ Create a parser that calls out to another, as yet unknown, parser. Note that the inner parser must be bound later, using hammer_bind_indirect(). This can be used to create recursive parsers.
+
+ Result token type: the type of whatever parser is bound to it with hammer_bind_indirect().
+ </description>
+ <code>
+ </code>
+ </function>
+
+ <function role="public" name="hammer_bind_indirect">
+ <proto>void hammer_bind_indirect(HParser p)</proto>
+ <summary>Set the inner parser of an indirect parser.</summary>
+ <description>
+ See hammer_indirect() for details.
+ </description>
+ <code>
+ </code>
+ </function>
+
+</extension>
--
GitLab