Initial commit

.gitignore

+cp2kparser/cp2kparser.egg-info

README.md

+# CP2K
+The NoMaD parser for CP2K. Under development.
+
+## QuickStart
+- Clone repository
+- Run setup by running the setup.py script:
+    $ python setup.py install --user
+- Run tests (TODO)
+
+## Structure
+Currently the python package is divided into three subpackages:
+ - Engines: Classes for parsing different type of files
+ - Generics: Generic utility classes and base classes
+ - Implementation: The classes that actually define the parser functionality.

cp2kparser/__init__.py

+#! /usr/bin/env python

cp2kparser/engines/__init__.py

+#! /usr/bin/env python

cp2kparser/engines/cp2kinputengine.py

+from collections import defaultdict
+from cp2kparser.generics.util import *
+
+
+#===============================================================================
+class CP2KInputEngine(object):
+    """Used to parse out a CP2K input file.
+
+    When given a file handle to a CP2K input file, this class attemts to parse
+    out it's structure into an accessible object tree. Because the input file
+    has such a clearly defined structure (unlike the output file of CP2K), it
+    is better to use a dedicated parser instead of regular expressions.
+    """
+    def __init__(self, cp2k_parser):
+        """
+        Args:
+            cp2k_parser: Instance of a CP2KParser or it's subclass. Allows
+            access to e.g. unified file reading methods.
+        """
+        self.cp2k_parser = cp2k_parser
+        self.root_section = None
+
+    def parse_input(self):
+        """Parses the given CP2K input string"""
+
+        # The input file should be quite small, so just get the entire contents
+        inp = self.cp2k_parser.get_file_contents("input")
+
+        root_section = InputSection('CP2K_INPUT')
+        section_stack = [root_section]
+
+        for line in inp.split('\n'):
+            line = line.split('!', 1)[0].strip()
+            if len(line) == 0:
+                continue
+
+            if line.upper().startswith('&END'):
+                s = section_stack.pop()
+            elif line[0] == '&':
+                parts = line.split(' ', 1)
+                name = parts[0][1:]
+                if len(parts) > 1:
+                    s = InputSection(name=name, params=parts[1].strip())
+                else:
+                    s = InputSection(name=name)
+                section_stack[-1].subsections[name.upper()].append(s)
+                section_stack.append(s)
+            else:
+                keyword_name = line.split(' ', 1)[0]
+                section_stack[-1].keywords[keyword_name].append(line)
+
+        self.root_section = root_section
+
+    def get_subsection(self, path, index=0):
+        return self.root_section.get_subsection(path, index)
+
+
+#===============================================================================
+class InputSection(object):
+    """Represents a section in a CP2K input file"""
+    def __init__(self, name, params=None):
+        self.name = name.upper()
+        self.params = params
+        self.keywords = defaultdict(list)
+        self.subsections = defaultdict(list)
+
+    def write(self):
+        """Outputs input section as string"""
+        output = []
+        for name, k_list in self.keywords.iteritems():
+            for value in k_list:
+                output.append(value)
+        for name, s_list in self.subsections.iteritems():
+            for s in s_list:
+                if s.params:
+                    output.append('&%s %s' % (s.name, s.params))
+                else:
+                    output.append('&%s' % s.name)
+                for l in s.write():
+                    output.append('   %s' % l)
+                output.append('&END %s' % s.name)
+        return output
+
+    def get_subsection(self, path, index=0):
+        """Finds a subsection specified by a string where subsections are
+        separated by a slash. If multiple subsections are found with the same
+        path, the one specified by the given index (default 0) is returned.
+
+        Example: get_subsection("FORCE_EVAL/PRINT/FORCES")
+
+        Args:
+            path: String indicating the path to the subsection
+            index: In case of repeating subsections, return the one specified
+            by this index.
+
+        Returns:
+            The InputSection object if found.
+
+        """
+        parts = path.upper().split('/', 1)
+        candidates = self.subsections.get(parts[0])    # [s for s in self.subsections if s.name == parts[0]]
+        if not candidates:
+            print_debug("Subsection '{}' not found.".format(parts[0]))
+            return None
+        elif len(candidates) > 1:
+            print_warning("Multiple subsections with the same name found with name '{}' If no index is given, the first occurence in the input file is returned.".format(parts[0]))
+        try:
+            subsection = candidates[index]
+        except IndexError:
+            print_error("Invalid subsection index given.")
+
+        if len(parts) == 1:
+            return subsection
+        return subsection.get_subsection(parts[1])
+
+    def get_keyword(self, keyword, index=0):
+        """Finds a keyword specified by a string. If multiple keywords are found with the same
+        name, the one specified by the given index (default 0) is returned.
+
+        Args:
+            keyword: String indicating the name of the keyword. The name is the
+            first word in the line.
+            index: In case of repeating keywords, return the one specified
+            by this index.
+
+        Returns:
+            The keyword value (everything else than the first word on the line).
+
+        """
+        candidates = self.keywords.get(keyword)    # [s for s in self.subsections if s.name == parts[0]]
+        if not candidates:
+            print_debug("No keywords with name '{}' found in subsection '{}'".format(keyword, self.name))
+            return None
+        elif len(candidates) > 1:
+            print_warning("Multiple keywords with the same name found with name '{}' If no index is given, the first occurence in the input file is returned.".format(parts[0]))
+        try:
+            result = candidates[index]
+        except IndexError:
+            print_error("Invalid keyword index given.")
+        return result
+
+    def get_parameter(self):
+        return self.params

cp2kparser/engines/regexengine.py

+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+import os
+from cp2kparser.generics.util import *
+try:
+    import re2 as re
+except ImportError:
+    import re
+    print_warning((
+        "re2 package not found. Using re package instead. "
+        "If you wan't to use re2 please see the following links:"
+        "    https://github.com/google/re2"
+        "    https://pypi.python.org/pypi/re2/"
+    ))
+else:
+    re.set_fallback_notification(re.FALLBACK_WARNING)
+
+
+#===============================================================================
+class Regex(object):
+    """Represents a regex search used by the RegexEngine class.
+
+    In addition to a regular regex object from the re2 or re  module, this
+    object wraps additional information about a regex search:
+
+        regex_string: The regular expression as a string. Supports also the
+        more verbose form
+        (https://docs.python.org/2/library/re.html#re.VERBOSE)
+
+        index: Index for the wanted match. Can be a single integer number (also
+        negative indices supported) or if the special value "all" is provided,
+        all results will be returned.
+
+        separator: If a separator is defined, the input file can be chopped
+        into smaller pieces which are separated by the given separator. The
+        separator is a strig representing a regular epression. The smaller pieces are
+        then searched independently. This approach allows bigger files to be
+        handled piece by piece without loading the whole file into memory.
+
+        direction: If a separator is defined, this parameter defines whether
+        the file is chopped into pieces starting from the end or from the
+        start.
+
+        from_beginning: If true, the input must match the regular expression
+        right from the start. Any matches in the middle of the input are not
+        searched.
+
+    """
+
+    def __init__(self, regex_string, index="all", separator=None, direction="down", from_beginning=False):
+        self.regex_string = regex_string
+        self.index = index
+        self.separator = separator
+        self.direction = direction
+        self.from_beginning = from_beginning
+        self.compiled_regex = None
+        self.compiled_separator = None
+        self.inner_regex = None
+
+        self.check_input()
+        self.compile()
+
+    def set_inner_regex(self, inner_regex):
+        self.inner_regex = inner_regex
+
+    def compile(self):
+        self.compiled_regex = re.compile(self.regex_string, re.VERBOSE)
+        self.compiled_separator = re.compile(self.separator, re.VERBOSE)
+
+    def check_input(self):
+        if self.direction != "down" and self.direction != "up":
+            print_error("Unsupported direction value '{}' in a regex".format(self.direction))
+
+    def match(self, string):
+        return self.compiled_regex.match(string)
+
+    def search(self, string):
+        return self.compiled_regex.search(string)
+
+    def findall(self, string):
+        return self.compiled_regex.search(string)
+
+    def finditer(self, string):
+        return self.compiled_regex.finditer(string)
+
+
+#===============================================================================
+class RegexEngine(object):
+    """Used for parsing values values from files with regular expressions.
+    """
+
+    def __init__(self, parser):
+        self.regexs = None
+        self.results = {}
+        self.regex_dict = {}
+        self.target_dict = {}
+        self.files = None
+        self.extractors = None
+        self.extractor_results = {}
+        self.output = None
+        self.regexs = None
+        self.cache = {}
+
+        self.compiled_regexs = {}
+        self.file_contents = {}
+
+    def parse(self, regex, file_handle):
+        """Use the given regex to parse contents from the given file handle"""
+
+        file_name = file_handle.name
+        print_debug("Searching regex in file '{}'".format(file_name))
+        result = self.recursive_extraction(regex, file_handle)
+        if result:
+            return result
+
+        # Couldn't find the quantity from any of the specified files
+        print_error("Could not find a result for {}.".format(regex.regex_string))
+
+    def recursive_extraction(self, regex, data):
+        """Goes through the exctractor tree recursively until the final
+        extractor is found and returns the value given by it. The value can be
+        of any dimension but contains only strings.
+        """
+
+        # # Early return with cached result
+        # result = self.extractor_results.get(extractor_id)
+        # if result:
+            # return result
+
+        result = None
+
+        # If separator specified, do a blockwise search
+        if regex.separator is not None:
+            print_debug("Going into blockwise regex search")
+            result = self.regex_block_search(data, regex)
+        # Regular string search
+        else:
+            print_debug("Going into full regex search")
+            result = self.regex_search_string(data, regex)
+
+        if not result:
+            print_error("There was an issue in regex '{}' with index '{}' .".format(regex.regex_string, regex.index))
+            return None
+
+        # See if the tree continues
+        if regex.inner_regex is not None:
+            print_debug("Entering next regex recursion level.")
+            return self.recursive_extraction(regex.inner_regex, result)
+        else:
+            return result
+
+    def regex_search_string(self, data, regex):
+        """Do a regex search on the data. This loads the entire data into so it
+        might not be the best option for big files. See 'regex_block_search'
+        for reading the file piece-by-piece.
+        """
+        from_beginning = regex.from_beginning
+        index = regex.index
+
+        # If given a file object, read all as string
+        if isinstance(data, file):
+            data.seek(0)
+            contents = data.read()
+        else:
+            contents = data
+
+        result = None
+        if from_beginning:
+            print_debug("Doing full string search from beginning.")
+            return regex.match(contents)
+        elif index == "all":
+            print_debug("Doing full string search for all results.")
+            result = regex.findall(contents)
+            if not result:
+                print_error("No matches.")
+        elif index >= 0:
+            print_debug("Doing full string search with specified index.")
+            iter = regex.finditer(contents)
+            i = 0
+            while i <= index:
+                try:
+                    match = iter.next()
+                except StopIteration:
+                    if i == 0:
+                        print_error("No results.")
+                    else:
+                        print_error("Invalid regex index.")
+                    break
+                if i == index:
+                    result = match.groups()[0]
+                i += 1
+        elif index < 0:
+            matches = regex.findall(contents)
+            if not matches:
+                print_error("No matches.")
+            else:
+                try:
+                    result = matches[index]
+                except IndexError:
+                    print_error("Invalid regex index.")
+
+        return result
+
+    def regex_block_search(self, file_handle, regex):
+        """Do a regex search on the data. This function can load the file piece
+        by piece to avoid loading huge files into memory. The piece-wise search
+        can also be used to search the file from bottom to up.
+        """
+        compiled_separator = regex.compiled_separator
+        separator = regex.separator
+        direction = regex.direction
+        index = regex.index
+        from_beginning = regex.from_beginning
+        print_debug("Doing blockwise search with separator: '{}', direction: '{}', from_beginning: '{}' and index '{}'".format(separator, direction, from_beginning, index))
+
+        # Determine the direction in which the blocks are read
+        if direction == "up":
+            print_debug("Searching from bottom to up.")
+            generator = self.reverse_block_generator(file_handle, compiled_separator)
+        elif direction == "down":
+            print_debug("Searching from up to bottom.")
+            generator = self.block_generator(file_handle, compiled_separator)
+        else:
+            print_error("Unknown direction specifier: {}".format(direction))
+            return
+
+        # If all results wanted, just get all results from all blocks
+        if index == "all":
+            results = []
+            for block in generator:
+                results += regex.findall(block)
+            return results
+
+        # If index given, search until the correct index found
+        i_result = 0
+        counter = 0
+        for block in generator:
+            counter += 1
+            if from_beginning:
+                result = regex.match(block)
+                if result:
+                    print_debug("Found match in beginning of block.")
+                    if index + 1 > i_result + 1:
+                        i_result += 1
+                    else:
+                        return result.groups()[0]
+            else:
+                results = regex.findall(block)
+                n_results = len(results)
+                if results:
+                    print_debug("Found results within block.")
+                    if index + 1 > i_result + n_results:
+                        i_result += n_results
+                    else:
+                        return results[i_result + (n_results-1) - index]
+
+    def reverse_block_generator(self, fh, separator, buf_size=1000000):
+        """A generator that returns chunks of a file piece-by-piece in reverse
+        order.
+        """
+        segment = None
+        offset = 0
+        fh.seek(0, os.SEEK_END)
+        total_size = remaining_size = fh.tell()
+        while remaining_size > 0:
+            offset = min(total_size, offset + buf_size)
+            fh.seek(-offset, os.SEEK_END)
+            buffer = fh.read(min(remaining_size, buf_size))
+            remaining_size -= buf_size
+            #print remaining_size
+            lines = separator.split(buffer)
+            # lines = buffer.split(separator)
+            # the first line of the buffer is probably not a complete line so
+            # we'll save it and append it to the last line of the next buffer
+            # we read
+            if segment is not None:
+                # if the previous chunk starts right from the beginning of line
+                # do not concact the segment to the last line of new chunk
+                # instead, yield the segment first
+                if not buffer.endswith(separator):
+                    lines[-1] += segment
+                else:
+                    yield segment
+            segment = lines[0]
+            for index in range(len(lines) - 1, 0, -1):
+                if len(lines[index]):
+                    yield lines[index]
+        yield segment
+
+    def block_generator(self, fh, separator, buf_size=1000000):
+        """A generator that returns chunks of a file piece-by-piece
+        """
+        segment = None
+        offset = 0
+        fh.seek(0, os.SEEK_END)
+        total_size = remaining_size = fh.tell()
+        fh.seek(0, os.SEEK_SET)
+        while remaining_size > 0:
+            offset = min(total_size, offset)
+            fh.seek(offset, os.SEEK_SET)
+            offset += buf_size
+            buffer = fh.read(min(remaining_size, buf_size))
+            remaining_size -= buf_size
+            lines = separator.split(buffer)
+            # lines = buffer.split(separator)
+            # the first line of the buffer is probably not a complete line so
+            # we'll save it and append it to the last line of the next buffer
+            # we read
+            if segment is not None:
+                # if the previous chunk starts right from the beginning of line
+                # do not concact the segment to the last line of new chunk
+                # instead, yield the segment first
+                if not buffer.startswith(separator):
+                    lines[0] = segment + lines[0]
+                else:
+                    yield segment
+            segment = lines[-1]
+            for index in range(0, len(lines) - 1, 1):
+                if len(lines[index]):
+                    yield lines[index]
+        yield segment

cp2kparser/engines/xyzengine.py

+from cp2kparser.generics.util import *
+import numpy as np
+from io import StringIO
+np_version = np.__version__
+split = np_version.split(".")
+if int(split[1]) < 10 and int(split[0] < 1):
+    print_warning("Using too old version of numpy, the XYZ Parsing may not work properly!")
+
+
+#===============================================================================
+class XYZEngine(object):
+    """Used to parse out XYZ and extended XYZ files.
+
+    When given a file handle to a CP2K input file, this class attemts to parse
+    out it's structure into an accessible object tree. Because the input file
+    has such a clearly defined structure (unlike the output file of CP2K), it
+    is better to use a dedicated parser instead of regular expressions.
+    """
+    def __init__(self, parser):
+        """
+        Args:
+            cp2k_parser: Instance of a CP2KParser or it's subclass. Allows
+            access to e.g. unified file reading methods.
+        """
+        self.parser = parser
+
+    def parse_file(self, file_handle, columns, exclusion_patterns):
+        """Parses floating point numbers from the given file using the given
+        columns.
+
+        The file handle should be opened and closed somewhere else. The columns
+        are used to extract only certain components form each line.
+
+        Returns:
+            A numpy array of floating point numbers.
+        """
+        converters = {}
+        for column in columns:
+            converters[column] = float
+        result = np.loadtxt(file_handle, dtype=np.float64, comments=exclusion_patterns, usecols=columns, converters=converters)
+        return result
+
+    def parse_string(self, string, columns, exclusion_patterns):
+        """Parses floating point numbers from the given string using the given
+        columns.
+
+        Returns:
+            3D numpy array of floating point numbers.
+        """
+        stream = StringIO(string)
+        return self.parse_file(stream, columns, exclusion_patterns)

cp2kparser/generics/__init__.py

+#! /usr/bin/env python

cp2kparser/generics/nomadparser.py

+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+import json
+import os
+import time
+from cp2kparser.generics.util import *
+
+
+#===============================================================================
+class NomadParser(object):
+    """The base class for a NoMaD parser.
+    """
+
+    def __init__(self, input_json_string):
+        self.input_json_string = input_json_string
+        self.input_json_object = None
+        self.files = {}
+        self.tmp_dir = None
+        self.metainfo_to_keep = None
+        self.metainfo_to_skip = None
+        self.file_ids = {}
+        self.file_handles = {}
+        self.interface_object = None
+        self.implementation = None
+        self.file_contents = {}
+        self.file_sizes = {}
+        self.results = {}
+
+    def get_file_contents(self, file_id):
+
+        cache_limit = 10000
+        contents = self.file_contents.get(file_id)
+        if not contents:
+            fh = self.file_handles[file_id]
+            fh.seek(0)
+            contents = fh.read()
+            if self.get_file_size(file_id) <= cache_limit:
+                self.file_contents[file_id] = contents
+        return contents
+
+    def get_file_size(self, file_id):
+
+        size = self.file_sizes.get(file_id)
+        if not size:
+            fh = self.file_handles[file_id]
+            fh.seek(0, os.SEEK_END)
+            size = fh.tell()
+            self.file_sizes[file_id] = size
+        return size
+
+