<?xml version="1.0" encoding="UTF-8"?>
<commits type="array">
  <commit>
    <parents type="array">
      <parent>
        <id>f94101f635c5972275a2a0406e7288f85c50e2e6</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/f6003043554ed41258037a8a8959161a704a4675</url>
    <id>f6003043554ed41258037a8a8959161a704a4675</id>
    <committed-date>2009-12-14T14:59:04-08:00</committed-date>
    <authored-date>2009-12-14T14:59:04-08:00</authored-date>
    <message>Use DiskQueue vs. List for ScoredUrlDatum objects.</message>
    <tree>8159f660f60cce679f11f014ea50ea26fc466252</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>1985f776f8b23283908fc31ceacfbf0e9cacffc9</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/f94101f635c5972275a2a0406e7288f85c50e2e6</url>
    <id>f94101f635c5972275a2a0406e7288f85c50e2e6</id>
    <committed-date>2009-12-14T14:58:36-08:00</committed-date>
    <authored-date>2009-12-14T14:58:36-08:00</authored-date>
    <message>Get rid of two annotations that Eclipse doesn't like.</message>
    <tree>202b7622ac56826e52673eedfadfbb191c958231</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>c7339210dd0e4ea49c9b7f2381e90d2c7a2541fc</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/1985f776f8b23283908fc31ceacfbf0e9cacffc9</url>
    <id>1985f776f8b23283908fc31ceacfbf0e9cacffc9</id>
    <committed-date>2009-12-14T14:58:18-08:00</committed-date>
    <authored-date>2009-12-14T14:58:18-08:00</authored-date>
    <message>Fixed comment error.</message>
    <tree>27d60c8b1fd1241c0c032cedfb43935238689d87</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>920f23fbc1a9e065c1c1ed18ac3446330f734a56</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/c7339210dd0e4ea49c9b7f2381e90d2c7a2541fc</url>
    <id>c7339210dd0e4ea49c9b7f2381e90d2c7a2541fc</id>
    <committed-date>2009-12-14T14:58:07-08:00</committed-date>
    <authored-date>2009-12-14T14:58:07-08:00</authored-date>
    <message>Cleaned up FetchPipe tests</message>
    <tree>06130ee0a1e07defd2e27c2f8da93d78703dda1e</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>1ce62281bb60d755e28a8151e382bde082cc3b4a</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/920f23fbc1a9e065c1c1ed18ac3446330f734a56</url>
    <id>920f23fbc1a9e065c1c1ed18ac3446330f734a56</id>
    <committed-date>2009-12-14T14:57:38-08:00</committed-date>
    <authored-date>2009-12-14T14:57:38-08:00</authored-date>
    <message>Fixed tests now that FetchPipe/FetcherQueue use DiskQueue and assume
that the URLs are sorted by score.</message>
    <tree>f62e3e4f16313a394241a317cf6e26a1d284a96b</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>f7c6eccbfcd98c6f5a37f16ee8e4fd33142f4af6</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/1ce62281bb60d755e28a8151e382bde082cc3b4a</url>
    <id>1ce62281bb60d755e28a8151e382bde082cc3b4a</id>
    <committed-date>2009-12-14T14:57:02-08:00</committed-date>
    <authored-date>2009-12-14T14:57:02-08:00</authored-date>
    <message>Re-enable test now that TIKA-339 is fixed.</message>
    <tree>f6a9f9866a3f2531f3153b2f2bd1c89b3b65c2b7</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>a19e5be543904c098681ca5b740a0f78babc216f</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/f7c6eccbfcd98c6f5a37f16ee8e4fd33142f4af6</url>
    <id>f7c6eccbfcd98c6f5a37f16ee8e4fd33142f4af6</id>
    <committed-date>2009-12-14T14:56:37-08:00</committed-date>
    <authored-date>2009-12-14T14:56:37-08:00</authored-date>
    <message>Fixed bug w/size() not including cached element.

Fixed bug w/not ensuring file is open before handling load request.

Added buffering for object output stream, for efficiency during many writes.

Added clear support, for efficiency when clearing out the queue.</message>
    <tree>652a4fb2ac371751bffa06c9213d97a4bd83684b</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>81a8173484aa1c08243d67aeea36d8a7418dbdd7</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/a19e5be543904c098681ca5b740a0f78babc216f</url>
    <id>a19e5be543904c098681ca5b740a0f78babc216f</id>
    <committed-date>2009-12-14T14:54:52-08:00</committed-date>
    <authored-date>2009-12-14T14:54:52-08:00</authored-date>
    <message>Document min response rate</message>
    <tree>ed12079b674749aa6fce9f270214b84075e806c2</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>a8cfc167e5bc6dce1c448974d18e5258ade7f132</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/81a8173484aa1c08243d67aeea36d8a7418dbdd7</url>
    <id>81a8173484aa1c08243d67aeea36d8a7418dbdd7</id>
    <committed-date>2009-12-14T14:54:40-08:00</committed-date>
    <authored-date>2009-12-14T14:54:40-08:00</authored-date>
    <message>Fix up &quot;helpful&quot; contrib for latest Cascading/Bixo</message>
    <tree>b053361f513fae0c3464fb73fdc908a5d4731525</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>3a8c919c8ae67d902f613eed24eb5dda296ad94e</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/a8cfc167e5bc6dce1c448974d18e5258ade7f132</url>
    <id>a8cfc167e5bc6dce1c448974d18e5258ade7f132</id>
    <committed-date>2009-12-14T14:54:06-08:00</committed-date>
    <authored-date>2009-12-14T14:54:06-08:00</authored-date>
    <message>First cut at Cascading filter that acts like the Debug filter but is tied
into Log4J.</message>
    <tree>9b712713722cd75db169b1a23dff796986709e04</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>f9b42dfdae3859b1b7ddcde5dc3ec86583858da9</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/3a8c919c8ae67d902f613eed24eb5dda296ad94e</url>
    <id>3a8c919c8ae67d902f613eed24eb5dda296ad94e</id>
    <committed-date>2009-12-11T17:22:40-08:00</committed-date>
    <authored-date>2009-12-11T17:22:40-08:00</authored-date>
    <message>Comment out failing test w/Cascading 1.1 &amp; Hadoop 0.18.3</message>
    <tree>d94a507d5e06476cd3f409dbc55b0c06c922d578</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>d8222ade5dbd31cd3e2bca6a693e412d59bd4206</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/f9b42dfdae3859b1b7ddcde5dc3ec86583858da9</url>
    <id>f9b42dfdae3859b1b7ddcde5dc3ec86583858da9</id>
    <committed-date>2009-12-11T17:22:08-08:00</committed-date>
    <authored-date>2009-12-11T17:22:08-08:00</authored-date>
    <message>Added first cut at DiskQueue, which uses temp file to spill
extra entries to disk. This will help us solve out of memory
errors during queue generation for both robots.txt and
FetcherBuffer processing.</message>
    <tree>d16b6e4a13b6800f8df5fd0ba7cf44a4646238e9</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>8aec1504729e194d6c1ed884191a759ba7bc9229</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/d8222ade5dbd31cd3e2bca6a693e412d59bd4206</url>
    <id>d8222ade5dbd31cd3e2bca6a693e412d59bd4206</id>
    <committed-date>2009-12-11T17:21:09-08:00</committed-date>
    <authored-date>2009-12-11T17:21:09-08:00</authored-date>
    <message>Added a safeClose for output streams.</message>
    <tree>19310e54778a981df7c6e67c9a30a28f3331d3e7</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>e19f2b508b3408a7671e5a0353c5f8a843cc709c</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/8aec1504729e194d6c1ed884191a759ba7bc9229</url>
    <id>8aec1504729e194d6c1ed884191a759ba7bc9229</id>
    <committed-date>2009-12-11T17:20:57-08:00</committed-date>
    <authored-date>2009-12-11T17:20:57-08:00</authored-date>
    <message>Protect against Hadoop 0.18.3 returning null when we
ask for a list of sub-directories. In 0.19.x you get
back an empty array of FileStatus objects.</message>
    <tree>cd5b9815e0ed946468c6a0c8ea5de1e401aec844</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>957495716bfeb7a870402872a8b0dd74ecdc7bd3</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/e19f2b508b3408a7671e5a0353c5f8a843cc709c</url>
    <id>e19f2b508b3408a7671e5a0353c5f8a843cc709c</id>
    <committed-date>2009-12-11T17:20:17-08:00</committed-date>
    <authored-date>2009-12-11T17:20:17-08:00</authored-date>
    <message>Minor comment cleanup</message>
    <tree>70d75c00cde0eb6ebe97d9ee2788b42f7871f792</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>386ccc208ac3bd79fd07a45210f97c21995c480c</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/957495716bfeb7a870402872a8b0dd74ecdc7bd3</url>
    <id>957495716bfeb7a870402872a8b0dd74ecdc7bd3</id>
    <committed-date>2009-12-11T17:20:09-08:00</committed-date>
    <authored-date>2009-12-11T17:20:09-08:00</authored-date>
    <message>Modified testing tool to also attempt to parse the fetched content,
to debug what's happening with some funky documents we're getting
back from Stanford.edu servers.</message>
    <tree>0d3f5068d036627a3b82a8b8b313837289005436</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>d579a0820fa201600759f784c14514b32c2f8037</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/386ccc208ac3bd79fd07a45210f97c21995c480c</url>
    <id>386ccc208ac3bd79fd07a45210f97c21995c480c</id>
    <committed-date>2009-12-11T17:19:32-08:00</committed-date>
    <authored-date>2009-12-11T17:19:32-08:00</authored-date>
    <message>First step in optimizing the fetch buffering process -
sort by score (reverse order) before calling FetcherBuffer
so that it can just start tossing URLs once it has enough.</message>
    <tree>3552287f2b17c480f3393c61f383972ffd08ad14</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>7b37b8ef04ef7e0ac89b750230b3e8a71241cb7b</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/d579a0820fa201600759f784c14514b32c2f8037</url>
    <id>d579a0820fa201600759f784c14514b32c2f8037</id>
    <committed-date>2009-12-11T17:18:53-08:00</committed-date>
    <authored-date>2009-12-11T17:18:53-08:00</authored-date>
    <message>Make sure the job doesn't get killed just because Tika throws
an Error (not an exception) during parsing.</message>
    <tree>f8c4c66e210949a4e9ffc19a651d9459071d9da3</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>ed124899da44ca09e5edc95754f240eb6f9ed1bf</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/7b37b8ef04ef7e0ac89b750230b3e8a71241cb7b</url>
    <id>7b37b8ef04ef7e0ac89b750230b3e8a71241cb7b</id>
    <committed-date>2009-12-11T17:18:28-08:00</committed-date>
    <authored-date>2009-12-11T17:18:28-08:00</authored-date>
    <message>Use new Cascading support to tell the flow planner that
we DO NOT want to be run twice, if a pipe split follows
the parse sub-assembly.</message>
    <tree>56020165cd728a6fc2a38f4804c65f758f1c8afa</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>7477240da1784672b06263bf3ed2c40bd64e32cc</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/ed124899da44ca09e5edc95754f240eb6f9ed1bf</url>
    <id>ed124899da44ca09e5edc95754f240eb6f9ed1bf</id>
    <committed-date>2009-12-11T17:18:04-08:00</committed-date>
    <authored-date>2009-12-11T17:18:04-08:00</authored-date>
    <message>Use new Cascading support to tell the flow planner that
we DO NOT want to be run twice, if a pipe split follows
the fetch sub-assembly.</message>
    <tree>7b933a0c979e6492fdc64bc556b817c3424e4caf</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>051b7910d3c77d03ed495eb1ece9c475fc4feb95</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/7477240da1784672b06263bf3ed2c40bd64e32cc</url>
    <id>7477240da1784672b06263bf3ed2c40bd64e32cc</id>
    <committed-date>2009-12-11T17:17:28-08:00</committed-date>
    <authored-date>2009-12-11T17:17:28-08:00</authored-date>
    <message>Don't throw exceptions for unknown HTTP status codes, as servers
are free to return whatever they damn well please (like 999).</message>
    <tree>dead3a6b185220cbbcad270559a1c9cbdeb616a7</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>9bd3357ed79d0872e56dd7e6448bc88e4c625321</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/051b7910d3c77d03ed495eb1ece9c475fc4feb95</url>
    <id>051b7910d3c77d03ed495eb1ece9c475fc4feb95</id>
    <committed-date>2009-12-11T17:17:00-08:00</committed-date>
    <authored-date>2009-12-11T17:17:00-08:00</authored-date>
    <message>Fix for Cascading 1.1</message>
    <tree>b7ad8f68784fb92d73542d578593ebf1c211cedd</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>ed03d02178f1244e4ded2fb7cb5024d5e276dad5</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/9bd3357ed79d0872e56dd7e6448bc88e4c625321</url>
    <id>9bd3357ed79d0872e56dd7e6448bc88e4c625321</id>
    <committed-date>2009-12-11T17:16:33-08:00</committed-date>
    <authored-date>2009-12-11T17:16:33-08:00</authored-date>
    <message>Switch to Cascading 1.1-WIP-84, since it fixes some issues with
running in EMR (long file names), and has support for marking
operations (like fetching &amp; parsing) as &quot;not safe&quot;, which means
they won't be done twice due to a following split.</message>
    <tree>0574349593b0b3609c654c7da43a57d2f4f844ce</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>ad89a30b669a57de51b3c959efd8b8c7ccda43b8</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/ed03d02178f1244e4ded2fb7cb5024d5e276dad5</url>
    <id>ed03d02178f1244e4ded2fb7cb5024d5e276dad5</id>
    <committed-date>2009-12-07T00:09:28-08:00</committed-date>
    <authored-date>2009-12-07T00:09:28-08:00</authored-date>
    <message>Remove noisy trace logging.

Handle files that are UTF-8 and have a BOM.</message>
    <tree>960e9b0d7c0f948a28f2cb21338b8534e6196897</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>9c6816e9e9dc0d73248aee65d03d1fd51b2ed7c1</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/ad89a30b669a57de51b3c959efd8b8c7ccda43b8</url>
    <id>ad89a30b669a57de51b3c959efd8b8c7ccda43b8</id>
    <committed-date>2009-12-07T00:08:30-08:00</committed-date>
    <authored-date>2009-12-07T00:08:30-08:00</authored-date>
    <message>Changed how we decide whether to abort the connection, to try
to catch cases of not closing things properly.</message>
    <tree>d51421a7f1890800158fbcf7d7690a1a58f7d4f7</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>f39ff6a57c47c71a45b82691e8b8da658fb11132</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/9c6816e9e9dc0d73248aee65d03d1fd51b2ed7c1</url>
    <id>9c6816e9e9dc0d73248aee65d03d1fd51b2ed7c1</id>
    <committed-date>2009-12-07T00:07:52-08:00</committed-date>
    <authored-date>2009-12-07T00:07:52-08:00</authored-date>
    <message>Added comments about problems I see with current FetcherManager
architecture.</message>
    <tree>2412bb63cf2b2e83d040dfefa371b8e5e4b44108</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>a3264caef0791eff546b47ae164a23d4381f87f5</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/f39ff6a57c47c71a45b82691e8b8da658fb11132</url>
    <id>f39ff6a57c47c71a45b82691e8b8da658fb11132</id>
    <committed-date>2009-12-07T00:07:23-08:00</committed-date>
    <authored-date>2009-12-07T00:07:23-08:00</authored-date>
    <message>Remove debug logging for typical situation of getting status
codes in 4xx and 5xx range.</message>
    <tree>778661852cf1b5f1f83677079cdc508484c1c049</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>8e102378bf8a70ed1b0bfca2751739e4740df4d5</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/a3264caef0791eff546b47ae164a23d4381f87f5</url>
    <id>a3264caef0791eff546b47ae164a23d4381f87f5</id>
    <committed-date>2009-12-06T19:03:38-08:00</committed-date>
    <authored-date>2009-12-06T19:03:38-08:00</authored-date>
    <message>Fixed bug w/not handling multiple ROBOTS attributes (comma separated).
For bullet-proofing, parse all attributes (break on comma).</message>
    <tree>14a52fd41b6d543638376223dad8f1c8f8b0a110</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>f2fadd1a91aea4f4a2531454a236a9ff61aa2ffd</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/8e102378bf8a70ed1b0bfca2751739e4740df4d5</url>
    <id>8e102378bf8a70ed1b0bfca2751739e4740df4d5</id>
    <committed-date>2009-12-06T19:03:01-08:00</committed-date>
    <authored-date>2009-12-06T19:03:01-08:00</authored-date>
    <message>Set the &quot;Acccept&quot; header to be mime-types we typically want, so we don't
get a bunch that we can't handle.</message>
    <tree>330ece7b472b1da65d74f99f851632e7cede642a</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
  <commit>
    <parents type="array">
      <parent>
        <id>0e4549507c6c55b7e1945c93713842bd00967b5f</id>
      </parent>
    </parents>
    <author>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </author>
    <url>http://github.com/emi/bixo/commit/f2fadd1a91aea4f4a2531454a236a9ff61aa2ffd</url>
    <id>f2fadd1a91aea4f4a2531454a236a9ff61aa2ffd</id>
    <committed-date>2009-12-06T19:01:40-08:00</committed-date>
    <authored-date>2009-12-06T19:01:40-08:00</authored-date>
    <message>Finished up adding support for aborting fetch due to invalid mime-type.</message>
    <tree>85cae52b6f625eb44a935001796cc92891f25c99</tree>
    <committer>
      <name>Ken Krugler</name>
      <email>kkrugler@transpac.com</email>
    </committer>
  </commit>
</commits>
