Python re.sub方法代码示例

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def test_quo9(self):
        #right: "<h5 id='id824837' onload='chat(\'id705147\',1,\' width=\\\'2pt\\\'\')'>"
        #                                                        ^  -- esc() --   ^
        #wrong: "<h5 id='id824837' onload='chat(\'id705147\',1,\\\' width=\\\'2pt\'\')'>"
        #                                                      ^  -- esc() --   ^
        w = Grammar("@id 8\n"
                    "root   \"<h5 id='\" id \"' onload='\" esc(func) \"'>\" #rclean\n"
                    "id     'id' [0-9]{6}\n"
                    "func   \"chat('\" id \"',\" [0-9] \",'\" esc(\" width='2pt'\") \"')\"\n"
                    , esc=lambda x:re.sub(r"('|\\)", r"\\\1", x))
        self.assertRegex(w.generate(), r"^<h5 id='id[0-9]{6}' onload='chat\(\\'id[0-9]{6}"
                                       r"\\',[0-9],\\' width=\\\\\\'2pt\\\\\\'\\'\)'>$")
        # same grammar with '@id' in chat() instead of 'id'
        w = Grammar("@id 8\n"
                    "root   \"<h5 id='\" id \"' onload='\" esc(func) \"'>\" #rclean\n"
                    "id     'id' [0-9]{6}\n"
                    "func   \"chat('\" @id \"',\" [0-9] \",'\" esc(\" width='2pt'\") \"')\"\n"
                    , esc=lambda x:re.sub(r"('|\\)", r"\\\1", x))
        self.assertRegex(w.generate(), r"^<h5 id='(id[0-9]{6})' onload='chat\(\\'\1"
                                       r"\\',[0-9],\\' width=\\\\\\'2pt\\\\\\'\\'\)'>$") 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def display(self):
        """
        Output the current progress string.
        """
        if self._io.is_quiet():
            return

        if self._format is None:
            self._set_real_format(
                self._internal_format or self._determine_best_format()
            )

        self._overwrite(
            re.sub(
                r"(?i)%([a-z\-_]+)(?::([^%]+))?%",
                self._overwrite_callback,
                self._format,
            )
        ) 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def test_quo9(self):
        #right: "<h5 id='id824837' onload='chat(\'id705147\',1,\' width=\\\'2pt\\\'\')'>"
        #                                                        ^  -- esc() --   ^
        #wrong: "<h5 id='id824837' onload='chat(\'id705147\',1,\\\' width=\\\'2pt\'\')'>"
        #                                                      ^  -- esc() --   ^
        w = Grammar("root   \"<h5 id='\" id \"' onload='\" esc(func) \"'>\"\n"
                    "id     'id' /[0-9]{6}/\n"
                    "func   \"chat('\" id \"',\" /[0-9]/ \",'\" esc(\" width='2pt'\") \"')\"\n"
                    , esc=lambda x: re.sub(r"('|\\)", r"\\\1", x))
        self.assertRegex(w.generate(), r"^<h5 id='id[0-9]{6}' onload='chat\(\\'id[0-9]{6}"
                                       r"\\',[0-9],\\' width=\\\\\\'2pt\\\\\\'\\'\)'>$")
        # same grammar with '@id' in chat() instead of 'id'
        w = Grammar("root   \"<h5 id='\" id \"' onload='\" esc(func) \"'>\"\n"
                    "id     'id' /[0-9]{6}/\n"
                    "func   \"chat('\" @id \"',\" /[0-9]/ \",'\" esc(\" width='2pt'\") \"')\"\n"
                    , esc=lambda x: re.sub(r"('|\\)", r"\\\1", x))
        self.assertRegex(w.generate(), r"^<h5 id='(id[0-9]{6})' onload='chat\(\\'\1"
                                       r"\\',[0-9],\\' width=\\\\\\'2pt\\\\\\'\\'\)'>$") 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def add_comp_one(compstr):
    """
    Adds stoichiometries of 1 to compstr that don't have them
    :param compstr:  composition as a string
    :return:         compositon with stoichiometries of 1 added
    """
    sample = re.sub(r"([A-Z])", r" \1", compstr).split()
    sample = ["".join(g) for _, g in groupby(str(sample), str.isalpha)]
    samp_new = ""
    for k in range(len(sample)):
        spl_samp = re.sub(r"([A-Z])", r" \1", sample[k]).split()
        for l in range(len(spl_samp)):
            if spl_samp[l][-1].isalpha() and spl_samp[l][-1] != "x":
                spl_samp[l] = spl_samp[l] + "1"
            samp_new += spl_samp[l]

    return samp_new 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def add_comp_one(compstr):
    """
    Adds stoichiometries of 1 to compstr that don't have them
    :param compstr:  composition as a string
    :return:         compositon with stoichiometries of 1 added
    """
    sample = pd.np.array(re.sub(r"([A-Z])", r" \1", compstr).split()).astype(str)
    sample = ["".join(g) for _, g in groupby(sample, str.isalpha)]
    samp_new = ""
    for k in range(len(sample)):
        spl_samp = re.sub(r"([A-Z])", r" \1", sample[k]).split()
        for l in range(len(spl_samp)):
            if spl_samp[l][-1].isalpha() and spl_samp[l][-1] != "x":
                spl_samp[l] = spl_samp[l] + "1"
            samp_new += spl_samp[l]
    return samp_new 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def parse_text(self,txt):
        err=udpipe.ProcessingError()
        tokenized=""
        current_block=[]
        for line in txt.split("\n"):
            if re.match(comment_regex, line.lstrip()): # comment line
                if current_block:
                    tokenized+=self.pipeline.process("\n".join(current_block),err)
                    current_block=[]
                tokenized+=re.sub(comment_regex, "# ", line.lstrip()+"\n")
                continue
            # normal text line, save to current block to be tokenized
            current_block.append(line)
        if current_block:
            tokenized+=self.pipeline.process("\n".join(current_block),err)
        return tokenized 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def update_sys_cfg_file(uninstall_distro_dir_name):
    """
    Main function to remove uninstall distro specific operations.
    :return:
    """

    sys_cfg_file = os.path.join(config.usb_mount, "multibootusb", "syslinux.cfg")
    if not os.path.exists(sys_cfg_file):
        gen.log("syslinux.cfg file not found for updating changes.")
    else:
        gen.log("Updating syslinux.cfg file...")
        string = open(sys_cfg_file).read()
        string = re.sub(r'#start ' + re.escape(uninstall_distro_dir_name)
                        + '.*?' + '#end '
                        + re.escape(uninstall_distro_dir_name)
                        + r'\s*', '', string, flags=re.DOTALL)
        config_file = open(sys_cfg_file, "w")
        config_file.write(string)
        config_file.close() 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def update_grub_cfg_file(uninstall_distro_dir_name):
    """
    Main function to remove uninstall distro name from the grub.cfg file.
    :return:
    """

    grub_cfg_file = os.path.join(config.usb_mount, "multibootusb",
                                 "grub", "grub.cfg")
    if not os.path.exists(grub_cfg_file):
        gen.log("grub.cfg file not found for updating changes.")
    else:
        gen.log("Updating grub.cfg file...")
        string = open(grub_cfg_file).read()
        string = re.sub(r'#start ' + re.escape(uninstall_distro_dir_name)
                        + '.*?' + '#end '
                        + re.escape(uninstall_distro_dir_name)
                        + r'\s*', '', string, flags=re.DOTALL)
        config_file = open(grub_cfg_file, "w")
        config_file.write(string)
        config_file.close() 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def buildPaginationHeader(resultCount, resultsPerPage, pageArg, url):
    """Build link header for result pagination"""
    lastPage = resultCount / resultsPerPage

    if pageArg:
        page = int(pageArg)
        next_url = re.sub("page=[0-9]+", "page={}".format(page + 1), url)
        prev_url = re.sub("page=[0-9]+", "page={}".format(page - 1), url)
        first_url = re.sub("page=[0-9]+", "page=1", url)
        last_url = re.sub("page=[0-9]+", "page={}".format(lastPage), url)
    else:
        page = 1
        next_url = url + "?page=2"
        prev_url = ""
        first_url = url + "?page=1"
        last_url = url + "?page={}".format(lastPage)

    if page == 1:
        headerLink = "<{}>; rel=next, <{}>; rel=last".format(next_url, last_url)
    elif page == lastPage:
        headerLink = "<{}>; rel=prev, <{}>; rel=first".format(prev_url, first_url)
    else:
        headerLink = "<{}>; rel=next, <{}>; rel=prev, <{}>; rel=first, <{}>; rel=last".format(next_url, prev_url, first_url, last_url)
    return headerLink 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def paginate_query(query, results_per_page, get_args):
    """Modify the given query so that it can be paginated. The paginated query will 
    split display a maximum of `results_per_page`."""
    page = get_args.get('page', 1)

    glogger.info("Paginating query for page {}, {} results per page".format(page, results_per_page))

    # If contains LIMIT or OFFSET, remove them
    glogger.debug("Original query: " + query)
    no_limit_query = re.sub("((LIMIT|OFFSET)\s+[0-9]+)*", "", query)
    glogger.debug("No limit query: " + no_limit_query)

    # Append LIMIT results_per_page OFFSET (page-1)*results_per_page
    paginated_query = no_limit_query + " LIMIT {} OFFSET {}".format(results_per_page,
                                                                    (int(page) - 1) * results_per_page)
    glogger.debug("Paginated query: " + paginated_query)

    return paginated_query 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def removeLines(mg):
    removeListFilePath = '/net/metagenomics/projects/PPSmg/data/V35/genome_ncbids.txt'
    #removeListFilePath = '/net/metagenomics/projects/PPSmg/data/V35/genome_accession_silva.txt'
    srcFilePath = str('/net/metagenomics/projects/PPSmg/data/markerGenes/db/' + mg + '_bact+arch_dnaV.tax')
    dstFilePath = str('/net/metagenomics/projects/PPSmg/data/V35/genomesRemoved/markerGenes/db/' + mg + '_bact+arch_dnaV.tax')
    #srcFilePath = str('/net/metagenomics/projects/PPSmg/data/silva/' + mg + '_silva106_ncbitax.bacteria+archaea.tax' )
    #dstFilePath = str('/net/metagenomics/projects/PPSmg/data/V35/genomesRemoved/silva/' + mg + '_silva106_ncbitax.bacteria+archaea.tax' )
    pattern = r'.*ncbid:([0-9]+)$'
    #pattern = r'^([^\-]+)\-.*$'

    removeSet = set(csv.getColumnAsList(removeListFilePath, colNum=0, comment='#'))
    col0 = csv.getColumnAsList(srcFilePath, colNum=0, sep='\t', comment='#')
    col1 = csv.getColumnAsList(srcFilePath, colNum=1, sep='\t', comment='#')
    out = csv.OutFileBuffer(dstFilePath)
    removed = 0
    for col0,col1 in zip(col0,col1):
        if re.sub(pattern, r'\1', col0) not in removeSet:
            out.writeText(str(col0 + '\t' + col1 + '\n'))
        else:
            removed += 1

    out.close()
    print mg, 'removeLines', removed 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def removeSequences(mg):
    removeListFilePath = '/net/metagenomics/projects/PPSmg/data/V35/genome_ncbids.txt'
    #removeListFilePath = '/net/metagenomics/projects/PPSmg/data/V35/genome_accession_silva.txt'
    srcFilePath = str('/net/metagenomics/projects/PPSmg/data/markerGenes/db/' + mg + '_bact+arch_dnaV.noalign.fna')
    dstFilePath = str('/net/metagenomics/projects/PPSmg/data/V35/genomesRemoved/markerGenes/db/' + mg + '_bact+arch_dnaV.noalign.fna')
    #srcFilePath = str('/net/metagenomics/projects/PPSmg/data/silva/' + mg + '_silva106_ncbitax.bacteria+archaea.fna' )
    #dstFilePath = str('/net/metagenomics/projects/PPSmg/data/V35/genomesRemoved/silva/' + mg + '_silva106_ncbitax.bacteria+archaea.fna' )
    pattern = r'.*ncbid:([0-9]+)$'
    #pattern = r'^([^\-]+)\-.*$'

    removeSet = set(csv.getColumnAsList(removeListFilePath, colNum=0, comment='#'))
    seqIdToSeq = fas.fastaFileToDict(srcFilePath)
    out = csv.OutFileBuffer(dstFilePath)
    removed = 0
    for seqId in seqIdToSeq:
        if re.sub(pattern, r'\1', str(seqId)) not in removeSet:
            out.writeText(str('>' + str(seqId) + '\n' + str(seqIdToSeq[seqId]) + '\n'))
        else:
            removed += 1

    out.close()
    print mg, 'removeSequences', removed 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def parse(self, line):
        lineArray = line.split()
        if len(lineArray) != 2:
            print '_MothurOutFileParser: wrong line', line
            return
        name = re.sub(r'^([0-9]+_[0-9]+)_[0-9]+_[0-9]+_[pr]+[0-2]$',r'\1', lineArray[0])
        tag = re.sub(r'^[0-9]+_[0-9]+_([0-9]+_[0-9]+_[pr]+[0-2])$',r'\1', lineArray[0])
        placementList = lineArray[1].replace('unclassified;', '').rsplit(';')
        if len(placementList) < 2:
            #print '_MothurOutFileParser: skip line', line
            return

        placement = placementList[-2]
        try:
            clade = int(re.sub('([0-9]+)\(.*', r'\1' , placement))
        except ValueError:
            return
        weight = float(re.sub('[0-9]+\(([0-9\.]+)\)', r'\1' , placement))

        entry = str(str(name) + '\t' + str(clade) + '\t' + str(weight) + '\t' + str(self.source) + '\t' + str(tag))
        if self.outBuffer.isEmpty():
            self.outBuffer.writeText(entry)
        else:
            self.outBuffer.writeText(str('\n' + entry)) 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def __init__(self, line):
        tokens = line.split(',')
        self._threshold = float(re.sub(r'^([^\t]+)\t[^\t]+\t.*', r'\1', tokens[0]))
        tokens[0] = re.sub(r'^[^\t]+\t[^\t]+\t(.*)', r'\1', tokens[0])
        self.groupIdCount = 0
        self.seqNameToGroupId = dict([])
        self.groupIdToSeqNameSet = dict([])
        for token in tokens:
            names = token.split('\t')
            self.groupIdToSeqNameSet[self.groupIdCount] = set([])
            for name in names:
                #print name
                if re.match(r'^[0-9]+_.*$', name):
                    seqName = re.sub(r'^([0-9]+_[0-9]+)_.*$',r'\1', name)
                    self.seqNameToGroupId[seqName] = self.groupIdCount
                    self.groupIdToSeqNameSet[self.groupIdCount].add(seqName)
            self.groupIdCount += 1 

# 需要导入模块: import re [as 别名]
# 或者: from re import sub [as 别名]
def _clean_str(string):
        """
        Tokenization/string cleaning for all datasets except for SST.
        Original taken from https://github.com/yoonkim/CNN_sentence/blob/master/process_data.py
        """
        string = re.sub(r"[^A-Za-z0-9(),!?\'\`]", " ", string)
        string = re.sub(r"\'s", " \'s", string)
        string = re.sub(r"\'ve", " \'ve", string)
        string = re.sub(r"n\'t", " n\'t", string)
        string = re.sub(r"\'re", " \'re", string)
        string = re.sub(r"\'d", " \'d", string)
        string = re.sub(r"\'ll", " \'ll", string)
        string = re.sub(r",", " , ", string)
        string = re.sub(r"!", " ! ", string)
        string = re.sub(r"\(", " \( ", string)
        string = re.sub(r"\)", " \) ", string)
        string = re.sub(r"\?", " \? ", string)
        string = re.sub(r"\s{2,}", " ", string)
        return string.strip().lower()