From a16ad12ae84c3534a8a9e841654c924a6d683d39 Mon Sep 17 00:00:00 2001 From: Krzysztof Rudnicki Date: Mon, 5 Jun 2023 23:35:58 +0200 Subject: [PATCH] feat: add flake support make it pylint compliant --- program/code/.flake8 | 2 + program/code/.pylintrc | 630 ++++++++++++++++++ program/code/main.py | 220 ++++-- .../test_translate_inside_to_html.py | 2 +- 4 files changed, 793 insertions(+), 61 deletions(-) create mode 100644 program/code/.flake8 create mode 100644 program/code/.pylintrc diff --git a/program/code/.flake8 b/program/code/.flake8 new file mode 100644 index 00000000..10e5a00f --- /dev/null +++ b/program/code/.flake8 @@ -0,0 +1,2 @@ +[flake8] +max-func-length=16 \ No newline at end of file diff --git a/program/code/.pylintrc b/program/code/.pylintrc new file mode 100644 index 00000000..93b9813a --- /dev/null +++ b/program/code/.pylintrc @@ -0,0 +1,630 @@ +[MAIN] + +# Analyse import fallback blocks. This can be used to support both Python 2 and +# 3 compatible code, which means that the block might have code that exists +# only in one or another interpreter, leading to false positives when analysed. +analyse-fallback-blocks=no + +# Clear in-memory caches upon conclusion of linting. Useful if running pylint +# in a server-like mode. +clear-cache-post-run=no + +# Load and enable all available extensions. Use --list-extensions to see a list +# all available extensions. +#enable-all-extensions= + +# In error mode, messages with a category besides ERROR or FATAL are +# suppressed, and no reports are done by default. Error mode is compatible with +# disabling specific errors. +#errors-only= + +# Always return a 0 (non-error) status code, even if lint errors are found. +# This is primarily useful in continuous integration scripts. +#exit-zero= + +# A comma-separated list of package or module names from where C extensions may +# be loaded. Extensions are loading into the active Python interpreter and may +# run arbitrary code. +extension-pkg-allow-list= + +# A comma-separated list of package or module names from where C extensions may +# be loaded. Extensions are loading into the active Python interpreter and may +# run arbitrary code. (This is an alternative name to extension-pkg-allow-list +# for backward compatibility.) +extension-pkg-whitelist= + +# Return non-zero exit code if any of these messages/categories are detected, +# even if score is above --fail-under value. Syntax same as enable. Messages +# specified are enabled, while categories only check already-enabled messages. +fail-on= + +# Specify a score threshold under which the program will exit with error. +fail-under=10 + +# Interpret the stdin as a python script, whose filename needs to be passed as +# the module_or_package argument. +#from-stdin= + +# Files or directories to be skipped. They should be base names, not paths. +ignore=CVS + +# Add files or directories matching the regular expressions patterns to the +# ignore-list. The regex matches against paths and can be in Posix or Windows +# format. Because '\\' represents the directory delimiter on Windows systems, +# it can't be used as an escape character. +ignore-paths= + +# Files or directories matching the regular expression patterns are skipped. +# The regex matches against base names, not paths. The default value ignores +# Emacs file locks +ignore-patterns=^\.# + +# List of module names for which member attributes should not be checked +# (useful for modules/projects where namespaces are manipulated during runtime +# and thus existing member attributes cannot be deduced by static analysis). It +# supports qualified module names, as well as Unix pattern matching. +ignored-modules= + +# Python code to execute, usually for sys.path manipulation such as +# pygtk.require(). +#init-hook= + +# Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the +# number of processors available to use, and will cap the count on Windows to +# avoid hangs. +jobs=1 + +# Control the amount of potential inferred values when inferring a single +# object. This can help the performance when dealing with large functions or +# complex, nested conditions. +limit-inference-results=100 + +# List of plugins (as comma separated values of python module names) to load, +# usually to register additional checkers. +load-plugins= + +# Pickle collected data for later comparisons. +persistent=yes + +# Minimum Python version to use for version dependent checks. Will default to +# the version used to run pylint. +py-version=3.11 + +# Discover python modules and packages in the file system subtree. +recursive=no + +# Add paths to the list of the source roots. Supports globbing patterns. The +# source root is an absolute path or a path relative to the current working +# directory used to determine a package namespace for modules located under the +# source root. +source-roots= + +# When enabled, pylint would attempt to guess common misconfiguration and emit +# user-friendly hints instead of false-positive error messages. +suggestion-mode=yes + +# Allow loading of arbitrary C extensions. Extensions are imported into the +# active Python interpreter and may run arbitrary code. +unsafe-load-any-extension=no + +# In verbose mode, extra non-checker-related info will be displayed. +#verbose= + + +[BASIC] + +# Naming style matching correct argument names. +argument-naming-style=snake_case + +# Regular expression matching correct argument names. Overrides argument- +# naming-style. If left empty, argument names will be checked with the set +# naming style. +#argument-rgx= + +# Naming style matching correct attribute names. +attr-naming-style=snake_case + +# Regular expression matching correct attribute names. Overrides attr-naming- +# style. If left empty, attribute names will be checked with the set naming +# style. +#attr-rgx= + +# Bad variable names which should always be refused, separated by a comma. +bad-names=foo, + bar, + baz, + toto, + tutu, + tata + +# Bad variable names regexes, separated by a comma. If names match any regex, +# they will always be refused +bad-names-rgxs= + +# Naming style matching correct class attribute names. +class-attribute-naming-style=any + +# Regular expression matching correct class attribute names. Overrides class- +# attribute-naming-style. If left empty, class attribute names will be checked +# with the set naming style. +#class-attribute-rgx= + +# Naming style matching correct class constant names. +class-const-naming-style=UPPER_CASE + +# Regular expression matching correct class constant names. Overrides class- +# const-naming-style. If left empty, class constant names will be checked with +# the set naming style. +#class-const-rgx= + +# Naming style matching correct class names. +class-naming-style=PascalCase + +# Regular expression matching correct class names. Overrides class-naming- +# style. If left empty, class names will be checked with the set naming style. +#class-rgx= + +# Naming style matching correct constant names. +const-naming-style=UPPER_CASE + +# Regular expression matching correct constant names. Overrides const-naming- +# style. If left empty, constant names will be checked with the set naming +# style. +#const-rgx= + +# Minimum line length for functions/classes that require docstrings, shorter +# ones are exempt. +docstring-min-length=-1 + +# Naming style matching correct function names. +function-naming-style=snake_case + +# Regular expression matching correct function names. Overrides function- +# naming-style. If left empty, function names will be checked with the set +# naming style. +#function-rgx= + +# Good variable names which should always be accepted, separated by a comma. +good-names=i, + j, + k, + ex, + Run, + _ + +# Good variable names regexes, separated by a comma. If names match any regex, +# they will always be accepted +good-names-rgxs= + +# Include a hint for the correct naming format with invalid-name. +include-naming-hint=no + +# Naming style matching correct inline iteration names. +inlinevar-naming-style=any + +# Regular expression matching correct inline iteration names. Overrides +# inlinevar-naming-style. If left empty, inline iteration names will be checked +# with the set naming style. +#inlinevar-rgx= + +# Naming style matching correct method names. +method-naming-style=snake_case + +# Regular expression matching correct method names. Overrides method-naming- +# style. If left empty, method names will be checked with the set naming style. +#method-rgx= + +# Naming style matching correct module names. +module-naming-style=snake_case + +# Regular expression matching correct module names. Overrides module-naming- +# style. If left empty, module names will be checked with the set naming style. +#module-rgx= + +# Colon-delimited sets of names that determine each other's naming style when +# the name regexes allow several styles. +name-group= + +# Regular expression which should only match function or class names that do +# not require a docstring. +no-docstring-rgx=^_ + +# List of decorators that produce properties, such as abc.abstractproperty. Add +# to this list to register other decorators that produce valid properties. +# These decorators are taken in consideration only for invalid-name. +property-classes=abc.abstractproperty + +# Regular expression matching correct type alias names. If left empty, type +# alias names will be checked with the set naming style. +#typealias-rgx= + +# Regular expression matching correct type variable names. If left empty, type +# variable names will be checked with the set naming style. +#typevar-rgx= + +# Naming style matching correct variable names. +variable-naming-style=snake_case + +# Regular expression matching correct variable names. Overrides variable- +# naming-style. If left empty, variable names will be checked with the set +# naming style. +#variable-rgx= + + +[CLASSES] + +# Warn about protected attribute access inside special methods +check-protected-access-in-special-methods=no + +# List of method names used to declare (i.e. assign) instance attributes. +defining-attr-methods=__init__, + __new__, + setUp, + asyncSetUp, + __post_init__ + +# List of member names, which should be excluded from the protected access +# warning. +exclude-protected=_asdict,_fields,_replace,_source,_make,os._exit + +# List of valid names for the first argument in a class method. +valid-classmethod-first-arg=cls + +# List of valid names for the first argument in a metaclass class method. +valid-metaclass-classmethod-first-arg=mcs + + +[DESIGN] +# List of regular expressions of class ancestor names to ignore when counting +# public methods (see R0903) +exclude-too-few-public-methods= + +# List of qualified class names to ignore when counting class parents (see +# R0901) +ignored-parents= + +# Maximum number of arguments for function / method. +max-args=5 + +# Maximum number of attributes for a class (see R0902). +max-attributes=7 + +# Maximum number of boolean expressions in an if statement (see R0916). +max-bool-expr=5 + +# Maximum number of branch for function / method body. +max-branches=12 + +# Maximum number of locals for function / method body. +max-locals=15 + +# Maximum number of parents for a class (see R0901). +max-parents=7 + +# Maximum number of public methods for a class (see R0904). +max-public-methods=20 + +# Maximum number of return / yield for function / method body. +max-returns=6 + +# Maximum number of statements in function / method body. +max-statements=50 + +# Minimum number of public methods for a class (see R0903). +min-public-methods=2 + + +[EXCEPTIONS] + +# Exceptions that will emit a warning when caught. +overgeneral-exceptions=builtins.BaseException,builtins.Exception + + +[FORMAT] + +# Expected format of line ending, e.g. empty (any line ending), LF or CRLF. +expected-line-ending-format= + +# Regexp for a line that is allowed to be longer than the limit. +ignore-long-lines=^\s*(# )??$ + +# Number of spaces of indent required inside a hanging or continued line. +indent-after-paren=4 + +# String used as indentation unit. This is usually " " (4 spaces) or "\t" (1 +# tab). +indent-string=' ' + +# Maximum number of characters on a single line. +max-line-length=100 + +# Maximum number of lines in a module. +max-module-lines=1000 + +# Allow the body of a class to be on the same line as the declaration if body +# contains single statement. +single-line-class-stmt=no + +# Allow the body of an if to be on the same line as the test if there is no +# else. +single-line-if-stmt=no + + +[IMPORTS] + +# List of modules that can be imported at any level, not just the top level +# one. +allow-any-import-level= + +# Allow explicit reexports by alias from a package __init__. +allow-reexport-from-package=no + +# Allow wildcard imports from modules that define __all__. +allow-wildcard-with-all=no + +# Deprecated modules which should not be used, separated by a comma. +deprecated-modules= + +# Output a graph (.gv or any supported image format) of external dependencies +# to the given file (report RP0402 must not be disabled). +ext-import-graph= + +# Output a graph (.gv or any supported image format) of all (i.e. internal and +# external) dependencies to the given file (report RP0402 must not be +# disabled). +import-graph= + +# Output a graph (.gv or any supported image format) of internal dependencies +# to the given file (report RP0402 must not be disabled). +int-import-graph= + +# Force import order to recognize a module as part of the standard +# compatibility libraries. +known-standard-library= + +# Force import order to recognize a module as part of a third party library. +known-third-party=enchant + +# Couples of modules and preferred modules, separated by a comma. +preferred-modules= + + +[LOGGING] + +# The type of string formatting that logging methods do. `old` means using % +# formatting, `new` is for `{}` formatting. +logging-format-style=old + +# Logging modules to check that the string format arguments are in logging +# function parameter format. +logging-modules=logging + + +[MESSAGES CONTROL] + +# Only show warnings with the listed confidence levels. Leave empty to show +# all. Valid levels: HIGH, CONTROL_FLOW, INFERENCE, INFERENCE_FAILURE, +# UNDEFINED. +confidence=HIGH, + CONTROL_FLOW, + INFERENCE, + INFERENCE_FAILURE, + UNDEFINED + +# Disable the message, report, category or checker with the given id(s). You +# can either give multiple identifiers separated by comma (,) or put this +# option multiple times (only on the command line, not in the configuration +# file where it should appear only once). You can also use "--disable=all" to +# disable everything first and then re-enable specific checks. For example, if +# you want to run only the similarities checker, you can use "--disable=all +# --enable=similarities". If you want to run only the classes checker, but have +# no Warning level messages displayed, use "--disable=all --enable=classes +# --disable=W". +disable=raw-checker-failed, + bad-inline-option, + locally-disabled, + file-ignored, + suppressed-message, + useless-suppression, + deprecated-pragma, + use-symbolic-message-instead + +# Enable the message, report, category or checker with the given id(s). You can +# either give multiple identifier separated by comma (,) or put this option +# multiple time (only on the command line, not in the configuration file where +# it should appear only once). See also the "--disable" option for examples. +enable=c-extension-no-member + + +[METHOD_ARGS] + +# List of qualified names (i.e., library.method) which require a timeout +# parameter e.g. 'requests.api.get,requests.api.post' +timeout-methods=requests.api.delete,requests.api.get,requests.api.head,requests.api.options,requests.api.patch,requests.api.post,requests.api.put,requests.api.request + + +[MISCELLANEOUS] + +# List of note tags to take in consideration, separated by a comma. +notes=FIXME, + XXX, + TODO + +# Regular expression of note tags to take in consideration. +notes-rgx= + + +[REFACTORING] + +# Maximum number of nested blocks for function / method body +max-nested-blocks=5 + +# Complete name of functions that never returns. When checking for +# inconsistent-return-statements if a never returning function is called then +# it will be considered as an explicit return statement and no message will be +# printed. +never-returning-functions=sys.exit,argparse.parse_error + + +[REPORTS] + +# Python expression which should return a score less than or equal to 10. You +# have access to the variables 'fatal', 'error', 'warning', 'refactor', +# 'convention', and 'info' which contain the number of messages in each +# category, as well as 'statement' which is the total number of statements +# analyzed. This score is used by the global evaluation report (RP0004). +evaluation=max(0, 0 if fatal else 10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10)) + +# Template used to display messages. This is a python new-style format string +# used to format the message information. See doc for all details. +msg-template= + +# Set the output format. Available formats are text, parseable, colorized, json +# and msvs (visual studio). You can also give a reporter class, e.g. +# mypackage.mymodule.MyReporterClass. +#output-format= + +# Tells whether to display a full report or only the messages. +reports=no + +# Activate the evaluation score. +score=yes + + +[SIMILARITIES] + +# Comments are removed from the similarity computation +ignore-comments=yes + +# Docstrings are removed from the similarity computation +ignore-docstrings=yes + +# Imports are removed from the similarity computation +ignore-imports=yes + +# Signatures are removed from the similarity computation +ignore-signatures=yes + +# Minimum lines number of a similarity. +min-similarity-lines=4 + + +[SPELLING] + +# Limits count of emitted suggestions for spelling mistakes. +max-spelling-suggestions=4 + +# Spelling dictionary name. No available dictionaries : You need to install +# both the python package and the system dependency for enchant to work.. +spelling-dict= + +# List of comma separated words that should be considered directives if they +# appear at the beginning of a comment and should not be checked. +spelling-ignore-comment-directives=fmt: on,fmt: off,noqa:,noqa,nosec,isort:skip,mypy: + +# List of comma separated words that should not be checked. +spelling-ignore-words= + +# A path to a file that contains the private dictionary; one word per line. +spelling-private-dict-file= + +# Tells whether to store unknown words to the private dictionary (see the +# --spelling-private-dict-file option) instead of raising a message. +spelling-store-unknown-words=no + + +[STRING] + +# This flag controls whether inconsistent-quotes generates a warning when the +# character used as a quote delimiter is used inconsistently within a module. +check-quote-consistency=no + +# This flag controls whether the implicit-str-concat should generate a warning +# on implicit string concatenation in sequences defined over several lines. +check-str-concat-over-line-jumps=no + + +[TYPECHECK] + +# List of decorators that produce context managers, such as +# contextlib.contextmanager. Add to this list to register other decorators that +# produce valid context managers. +contextmanager-decorators=contextlib.contextmanager + +# List of members which are set dynamically and missed by pylint inference +# system, and so shouldn't trigger E1101 when accessed. Python regular +# expressions are accepted. +generated-members= + +# Tells whether to warn about missing members when the owner of the attribute +# is inferred to be None. +ignore-none=yes + +# This flag controls whether pylint should warn about no-member and similar +# checks whenever an opaque object is returned when inferring. The inference +# can return multiple potential results while evaluating a Python object, but +# some branches might not be evaluated, which results in partial inference. In +# that case, it might be useful to still emit no-member and other checks for +# the rest of the inferred objects. +ignore-on-opaque-inference=yes + +# List of symbolic message names to ignore for Mixin members. +ignored-checks-for-mixins=no-member, + not-async-context-manager, + not-context-manager, + attribute-defined-outside-init + +# List of class names for which member attributes should not be checked (useful +# for classes with dynamically set attributes). This supports the use of +# qualified names. +ignored-classes=optparse.Values,thread._local,_thread._local,argparse.Namespace + +# Show a hint with possible names when a member name was not found. The aspect +# of finding the hint is based on edit distance. +missing-member-hint=yes + +# The minimum edit distance a name should have in order to be considered a +# similar match for a missing member name. +missing-member-hint-distance=1 + +# The total number of similar names that should be taken in consideration when +# showing a hint for a missing member. +missing-member-max-choices=1 + +# Regex pattern to define which classes are considered mixins. +mixin-class-rgx=.*[Mm]ixin + +# List of decorators that change the signature of a decorated function. +signature-mutators= + + +[VARIABLES] + +# List of additional names supposed to be defined in builtins. Remember that +# you should avoid defining new builtins when possible. +additional-builtins= + +# Tells whether unused global variables should be treated as a violation. +allow-global-unused-variables=yes + +# List of names allowed to shadow builtins +allowed-redefined-builtins= + +# List of strings which can identify a callback function by name. A callback +# name must start or end with one of those strings. +callbacks=cb_, + _cb + +# A regular expression matching the name of dummy variables (i.e. expected to +# not be used). +dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_ + +# Argument names that match this expression will be ignored. +ignored-argument-names=_.*|^ignored_|^unused_ + +# Tells whether we should check for unused import in __init__ files. +init-import=no + +# List of qualified module names which can have objects that can redefine +# builtins. +redefining-builtins-modules=six.moves,past.builtins,future.builtins,builtins,io diff --git a/program/code/main.py b/program/code/main.py index f81ba830..71b337d8 100644 --- a/program/code/main.py +++ b/program/code/main.py @@ -4,29 +4,51 @@ def command_name_check(latex_string, command_name): + """ + Checks if command name given from latex was spelled correctly + """ if latex_string[1: (len(command_name) + 1)] != command_name: print(latex_string + "Error! command misspeled!") return "Error!" - return + return "" def generic_checks(latex_string): + """ + Checks if string is given and whether latex parameters + ends with curly bracket + """ if latex_string == "": print(latex_string + "Error! No input given to function") return "Error!" if "}" not in latex_string: print(latex_string + "Error! curly bracket not closed!") return "Error!" - return + return "" def generic_checks_command(latex_string): + """ + In additon to generic checks it also checks if command starts with \ + """ if generic_checks(latex_string) == "Error!": return "Error!" if latex_string[0] != "\\": print(latex_string + "Error! has no slash at begining") return "Error!" - return + return "" + + +def document_class_only_checks(latex_string): + """ + Checks only errors connected to document class + """ + if latex_string[len("\\documentclass{") - 1] != "{": + print(latex_string + "Error! curly bracket not opened!") + return "Error!" + if command_name_check(latex_string, "documentclass") == "Error!": + return "Error!" + return "" def document_class(latex_string): @@ -36,13 +58,10 @@ def document_class(latex_string): """ if generic_checks_command(latex_string) == "Error!": return "Error!" - if latex_string[len("\\documentclass{") - 1] != "{": - print(latex_string + "Error! curly bracket not opened!") + if document_class_only_checks(latex_string) == "Error!": return "Error!" - if command_name_check(latex_string, "documentclass") == "Error!": - return "Error!" - document_type = latex_string[len( - "\\documentclass{"): (len(latex_string) - 1)] + # document_type = latex_string[len( + # "\\documentclass{"): (len(latex_string) - 1)] return "" @@ -81,24 +100,28 @@ def tabular_parameters(latex_string): def only_pipes_and_space(latex_string): - """Checks if latex string only contains | or " ", if yes returns True, if no returns false""" - return all(char == '|' or char == ' ' or char == '{' or char == '}' for char in latex_string) + """Checks if latex string only contains | or " " + if yes returns True, if no returns false""" + return all(char in ("|", " ", "{", "}") for char in latex_string) def main_tabular_parameters_loop(latex_string, simple_parameters_dictionary): + """ + Converts simple and paragraph table parameters into html style code + """ return_array = [] i = 0 latex_string_length = len(latex_string) while i < latex_string_length: character = latex_string[i] - if character in ['l', 'c', 'r', '|']: + if character in ["l", "c", "r", "|"]: return_array.append( simple_parameters_dictionary.get(latex_string[i])) i += 1 continue - if character in ['p', 'm', 'b']: - closing_bracket = latex_string.find('}', i + 1) - columns_string = latex_string[i:closing_bracket + 1] + if character in ["p", "m", "b"]: + closing_bracket = latex_string.find("}", i + 1) + columns_string = latex_string[i: closing_bracket + 1] result = tabular_columns_parameters(columns_string) if result == "Error!": return result @@ -109,57 +132,83 @@ def main_tabular_parameters_loop(latex_string, simple_parameters_dictionary): return return_array -def tabular_required_parameters(latex_string): +def tabular_required_errors(latex_string): + """ + Runs generic checks and + checks if there are any parameters put to latex table + """ if generic_checks(latex_string) == "Error!": return "Error!" if latex_string == "{}": - print("tabular_required_parameters, required table parameters are empty!:", latex_string) + print( + """tabular_required_parameters + required table parameters are empty!:""", + latex_string, + ) + return "Error!" + return "" + + +def tabular_required_parameters(latex_string): + """ + Converts simple tabular parameters to html style commands + """ + if tabular_required_errors(latex_string) == "Error!": return "Error!" simple_parameters_dictionary = { "l": "align='left'", "c": "align='center'", "r": "align='right'", - "|": "style='border-left: 1px solid black'" + "|": "style='border-left: 1px solid black'", } if only_pipes_and_space(latex_string): - print("tabular_required_parameters, required table parameters are only pipes and spaces!:", latex_string) + print( + """tabular_required_parameters, + required table parameters are only pipes and spaces!:""", + latex_string, + ) return "Error!" - return main_tabular_parameters_loop(latex_string, simple_parameters_dictionary) + return main_tabular_parameters_loop( + latex_string, simple_parameters_dictionary) def length_conversions(latex_length): + """ + Converts latex lengths to html lengths + """ length_dictionary = { "pt": [1.3, "px"], - "mm": [1, "mm"], - "cm": [1, "cm"], - "in": [1, "in"], - "ex": [1, "ex"], - "em": [1, "em"], } return length_dictionary.get(latex_length, "Error!") def tabular_columns_parameters(latex_string): + """ + Handles tabular paragraph parameters and translates them to html style + """ if generic_checks(latex_string) == "Error!": return "Error!" parameter_dictionary = { "p": "vertical-align: top;", "m": "vertical-align: middle;", - "b": "vertical-align: bottom;" + "b": "vertical-align: bottom;", } vertical_align_type = parameter_dictionary.get(latex_string[0], "Error!") if vertical_align_type == "Error!": print("tabular_columns_parameters, unknown parameter: ", latex_string[0]) return "Error!" - if latex_string[1] != '{': + if latex_string[1] != "{": print( - "tabular_columns_parameters, parameter length does not start with {", latex_string) + """tabular_columns_parameters + parameter length does not start with {""", + latex_string, + ) return "Error!" length_parameter_with_bracket = latex_string.partition("{")[2] length_parameter = length_parameter_with_bracket.partition("}")[0] @@ -173,37 +222,55 @@ def tabular_columns_parameters(latex_string): length_unit = length_parameter[i:] conversed_unit = length_conversions(length_unit) if conversed_unit == "Error!": - print("tabular_columns_parameters, Unit could not be conversed!", latex_string) + print("""tabular_columns_parameters, + Unit could not be conversed!""", latex_string) return "Error!" final_length = round(float(length_value) * conversed_unit[0], 2) - return_string = "style='" + vertical_align_type + \ - " width: " + str(final_length) + conversed_unit[1] + ";'" + return_string = ( + "style='" + + vertical_align_type + + " width: " + + str(final_length) + + conversed_unit[1] + + ";'" + ) return return_string def split_rows(latex_string): + """ + Splits table row string into separate strings and puts them in array + """ double_backslash = "\\" rows = latex_string.split(double_backslash) return rows def split_columns(table_row, column_count): + """ + Splits table row columns into separate strings and puts them in array + """ columns = table_row.split("&") - if len(columns) != column_count and columns != ['']: - + if len(columns) != column_count and columns != [""]: return "Error!" return columns def translate_column(latex_column): - hline_string_literal = "\hline" + """ + Translate insides of a single latex tabular column to html + """ + hline_string_literal = "\\hline" replaced_hline = latex_column.replace(hline_string_literal, "
") - replaced_newline = replaced_hline.replace('\newline', "
") + replaced_newline = replaced_hline.replace("\newline", "
") return replaced_newline def translate_inside_to_html(latex_table_inside, column_style): - return_string = " " + """ + Translates entire table insides to html + """ + return_string = "
" column_amount = 0 line_string = "style='border-left: 1px solid black'" for style in column_style: @@ -219,7 +286,9 @@ def translate_inside_to_html(latex_table_inside, column_style): return_string += "" return_string += "" - return_string += "
= len(column_style): print( - f"Error! column_number index: {column_number} is out of length of column_style: {column_style}") + f"""Error! column_number index: {column_number} + is out of length of column_style: {column_style}""" + ) return "Error!" current_style = column_style[column_number] while current_style == line_string: @@ -233,45 +302,65 @@ def translate_inside_to_html(latex_table_inside, column_style): return_string += "
" + return_string += "" return return_string def read_file(tex_filename): - tex_file = open(tex_filename, "r") - data = tex_file.read().replace('\n', '') - tex_file.close() + """ + opens, reads and saves latex file + content into python string, then closes file + """ + with open(tex_filename, "r", encoding="UTF-8") as tex_file: + data = tex_file.read().replace("\n", "") + tex_file.close() return data def read_document_class(latex_full_string): - document_class_index = latex_full_string.find("\documentclass") + """ + Finds documentclass in latex file and checks function correctness + """ + document_class_index = latex_full_string.find("\\documentclass") if document_class_index == -1: print("Main function error! documentclass not found") return "Error!" document_class_close_bracket = latex_full_string.find( "}", document_class_index) - document_class_string = latex_full_string[document_class_index:document_class_close_bracket + 1] - latex_full_string = latex_full_string[document_class_close_bracket + 1:len( - latex_full_string) - 1] + document_class_string = latex_full_string[ + document_class_index: document_class_close_bracket + 1 + ] + latex_full_string = latex_full_string[ + document_class_close_bracket + 1: len(latex_full_string) - 1 + ] return document_class(document_class_string), latex_full_string def read_begin_document(latex_full_string): + """ + Finds LaTeX \begin{document} command and returns html counterpart to it + """ begin_document_index = latex_full_string.find(r"\begin{document}") if begin_document_index == -1: print("read_begin_document error! begin{document not found") return "Error!", latex_full_string begin_document_close_bracket = latex_full_string.find( "}", begin_document_index) - begin_document_string = latex_full_string[begin_document_index:begin_document_close_bracket + 1] - latex_full_string = latex_full_string[begin_document_close_bracket + 1:len( - latex_full_string) - 1] + begin_document_string = latex_full_string[ + begin_document_index: begin_document_close_bracket + 1 + ] + latex_full_string = latex_full_string[ + begin_document_close_bracket + 1: len(latex_full_string) - 1 + ] return_string = begin_document(begin_document_string) return return_string, latex_full_string def read_start(html_string, data): + """ + Finds, reads latex document class + and begin document and translates them to html + """ document_class_result, data = read_document_class(data) if document_class_result == "Error!": return "Error!", data @@ -285,24 +374,29 @@ def read_start(html_string, data): def handle_table_whole(html_string, data, table_start, table_end): + """ + Reads entire table, handles its parameters + and insides and translates to html + """ if table_start == -1 or table_end == -1: return html_string, data tabular_begin_string = r"\begin{tabular}" - tabular_end_string = r"\end{tabular}" - table_part = data[table_start:table_end+len(tabular_end_string)] parameters_start_index = data.find( "{", table_start + len(tabular_begin_string)) parameters_end_index = data.find("}", parameters_start_index) - parameters_string = data[parameters_start_index:parameters_end_index+1] + parameters_string = data[parameters_start_index: parameters_end_index + 1] parameters_array = tabular_required_parameters(parameters_string) - inside_table = data[parameters_end_index+1:table_end] + inside_table = data[parameters_end_index + 1: table_end] html_string += translate_inside_to_html(inside_table, parameters_array) return html_string def handle_insides(html_string, data): + """ + Finds inside of table and translates them to html + """ tabular_index = 0 tabular_end_string = r"\end{tabular}" while tabular_index != -1: @@ -312,19 +406,25 @@ def handle_insides(html_string, data): return html_string, data html_string += data[0:tabular_index_start] - html_string = handle_table_whole(html_string, data, - tabular_index_start, tabular_index_end) - data = data[tabular_index_end + len(tabular_end_string):len(data)] + html_string = handle_table_whole( + html_string, data, tabular_index_start, tabular_index_end + ) + data = data[tabular_index_end + len(tabular_end_string): len(data)] tabular_index = tabular_index_end return html_string, data def main_function(tex_filename): + """ + Ran by default by program, + gets latex file and translates to html + """ data = read_file(tex_filename) html_string = "" html_string, data = read_start(html_string, data) if html_string == "Error!": - print("main_function error! when reading documentclass or begin document") + print("""main_function error! + when reading documentclass or begin document""") return "Error" html_string, data = handle_insides(html_string, data) @@ -332,7 +432,7 @@ def main_function(tex_filename): if __name__ == "__main__": - tex_filename = "texfile.tex" - final_html = main_function(tex_filename) - f = open(tex_filename + ".html", "w") - f.write(final_html) + TEX_FILENAME = "texfile.tex" + FINAL_HTML = main_function(TEX_FILENAME) + with open(TEX_FILENAME + ".html", "w", encoding="UTF-8") as f: + f.write(FINAL_HTML) diff --git a/program/unit_tests/test_code/test_translate_inside_to_html.py b/program/unit_tests/test_code/test_translate_inside_to_html.py index 5979c737..db469183 100644 --- a/program/unit_tests/test_code/test_translate_inside_to_html.py +++ b/program/unit_tests/test_code/test_translate_inside_to_html.py @@ -6,7 +6,7 @@ def given_correct_then_correct(): latex_string = "test & 2 & test \\ 4 & 5 & 6 \\" parameters_string = "{ l | c | r }" column_styles = tabular_required_parameters(parameters_string) - assert translate_inside_to_html(latex_string, column_styles) == "
test 2 test
4 5 6
" + assert translate_inside_to_html(latex_string, column_styles) == "
test 2 test
4 5 6
" def test_translate_inside_to_html():